INDEX

Explanations

pronouns or noun phrases denoting a group of people

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating individuals or groups

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

 Peak

-0.72

tains

-0.64

Applications

-0.61

 immunity

-0.60

pires

-0.60

 Outside

-0.58

 Gore

-0.56

 premature

-0.56

 Fail

-0.56

 Unlimited

-0.55

POSITIVE LOGITS

'll

1.00

're

0.96

've

0.92

ngth

0.86

'd

0.82

bsite

0.81

ald

0.79

ggy

0.78

bart

0.76

'm

0.75

Activations Density 0.287%

pronouns or noun phrases denoting a group of people

pronouns indicating individuals or groups

No Comments

No Known Activations