INDEX

Explanations

legal or political terms and actions

oai_token-act-pair · gpt-3.5-turbo

references to legal or regulatory decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 ILCS

-0.68

inis

-0.65

 Temper

-0.63

english

-0.60

TPPStreamerBot

-0.60

!.

-0.58

Rated

-0.58

 Flavoring

-0.56

 Osiris

-0.56

(@

-0.55

POSITIVE LOGITS

 amounted

0.96

 proves

0.88

 could

0.87

 violates

0.84

 stemmed

0.84

 represents

0.83

 shouldn

0.81

 signifies

0.80

isn

0.79

 constitutes

0.79

Activations Density 0.444%

legal or political terms and actions

references to legal or regulatory decisions

No Comments

No Known Activations