INDEX

Explanations

proper names

oai_token-act-pair · gpt-3.5-turbo

references to people's names

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

awar

-0.74

*/(

-0.74

unin

-0.74

hire

-0.72

heimer

-0.72

umbn

-0.71

olesc

-0.70

shit

-0.69

abol

-0.69

fare

-0.68

POSITIVE LOGITS

 Lynn

1.04

 Louise

1.01

 Patricia

1.00

 Marie

0.98

 Nicole

0.95

 Jane

0.92

 Garcia

0.92

 Gloria

0.91

 Lopez

0.91

Sue

0.91

Activations Density 0.065%

proper names

references to people's names

No Comments

No Known Activations