INDEX

Explanations

phrases related to legal offices or positions of authority

oai_token-act-pair · gpt-3.5-turbo

words related to legal offices and justice systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

stable

-0.72

paren

-0.64

natural

-0.63

ENTION

-0.61

 cessation

-0.61

âĵĺ

-0.61

raid

-0.60

¥ŀ

-0.60

 qualitative

-0.59

band

-0.59

POSITIVE LOGITS

ices

1.05

heet

0.88

mith

0.86

cale

0.85

onne

0.81

 Aires

0.81

ource

0.76

gal

0.75

riers

0.75

ync

0.74

Activations Density 0.017%

phrases related to legal offices or positions of authority

words related to legal offices and justice systems

No Comments

No Known Activations