INDEX

Explanations

names or references to individuals

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly prominent figures and their connections

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

ista

-0.75

 oats

-0.72

emonium

-0.71

istas

-0.71

Leaks

-0.69

CTV

-0.69

notations

-0.68

ing

-0.67

ingo

-0.66

llular

-0.62

POSITIVE LOGITS

bard

0.83

rosis

0.82

etr

0.80

chel

0.78

iat

0.77

 proble

0.76

rich

0.75

itability

0.71

rod

0.70

nil

0.69

Activations Density 0.052%

names or references to individuals

names of individuals, particularly prominent figures and their connections

No Comments

No Known Activations