INDEX

Explanations

words related to specific names and locations

oai_token-act-pair · gpt-3.5-turbo

specific names and references related to notable individuals and their achievements

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

 Wonderland

-0.76

ĨĴ

-0.71

theless

-0.70

 Palest

-0.66

 SERV

-0.66

 ACTIONS

-0.65

FUL

-0.62

inea

-0.61

 Franch

-0.60

Reviewer

-0.60

POSITIVE LOGITS

oshenko

0.82

uv

0.80

akura

0.77

arnaev

0.75

yip

0.75

jen

0.74

uden

0.72

shirts

0.71

oval

0.71

chnology

0.68

Activations Density 0.760%

words related to specific names and locations

specific names and references related to notable individuals and their achievements

No Comments

No Known Activations