INDEX

Explanations

legal terms and phrases

oai_token-act-pair · gpt-3.5-turbo

terms related to scrutiny and standards in a legal or regulatory context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Marketable

-0.73

 Whit

-0.71

 Manhattan

-0.69

 Shattered

-0.64

 Somerset

-0.64

 exhib

-0.62

 visitor

-0.62

 cottage

-0.62

 scene

-0.62

Syd

-0.62

POSITIVE LOGITS

¬

1.14

Ĵ

1.04

Ļ

1.01

ĸ

0.94

Ķ

0.93

ı

0.92

ľ

0.92

ĺ

0.91

¤

0.88

¡

0.88

Activations Density 0.231%

legal terms and phrases

terms related to scrutiny and standards in a legal or regulatory context

No Comments

No Known Activations