INDEX

Explanations

words related to legal and authoritative terms or documents

oai_token-act-pair · gpt-3.5-turbo

references to the Supreme Court and its related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Lens

-0.79

sbm

-0.77

housing

-0.69

gas

-0.68

house

-0.66

Ð´

-0.66

Widget

-0.65

 Dull

-0.64

ories

-0.64

Bloom

-0.63

POSITIVE LOGITS

reme

1.32

rising

0.89

olicy

0.88

ersed

0.87

ogun

0.76

ership

0.76

rase

0.75

lux

0.75

rise

0.75

ratulations

0.74

Activations Density 0.036%

words related to legal and authoritative terms or documents

references to the Supreme Court and its related terminology

No Comments

No Known Activations