INDEX

Explanations

scientific terms or names related to astronomy

oai_token-act-pair · gpt-3.5-turbo

suffixes and word endings that are common in various contexts, particularly focusing on 'ck', 'ren', and other recurring letter patterns

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owship

-0.70

itu

-0.69

oru

-0.61

 Neighbor

-0.60

asury

-0.58

 repay

-0.58

advertisement

-0.57

 Avalon

-0.57

 parasitic

-0.57

pay

-0.56

POSITIVE LOGITS

theless

0.75

uese

0.73

berra

0.66

ried

0.63

opolis

0.62

auld

0.62

lation

0.58

WER

0.58

Discover

0.58

atron

0.58

Activations Density 0.249%

scientific terms or names related to astronomy

suffixes and word endings that are common in various contexts, particularly focusing on 'ck', 'ren', and other recurring letter patterns

No Comments

No Known Activations