INDEX

Explanations

words related to legal matters and disobedience towards authority

oai_token-act-pair · gpt-3.5-turbo

terms related to legal contempt and offenses

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

ighed

-0.82

illon

-0.75

 Lumpur

-0.74

·

-0.72

pton

-0.72

ta

-0.70

tted

-0.70

alle

-0.70

abouts

-0.70

ichi

-0.69

POSITIVE LOGITS

uously

1.10

uous

1.07

 charges

0.78

 lashes

0.77

orously

0.77

 leveled

0.76

ously

0.76

 convictions

0.76

 writ

0.75

 contempt

0.74

Activations Density 0.041%

words related to legal matters and disobedience towards authority

terms related to legal contempt and offenses

No Comments

No Known Activations