INDEX

Explanations

terms related to legislative or regulatory actions

oai_token-act-pair · gpt-3.5-turbo

the term "polluter" and its variations related to environmental impact

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

ĪĴ

-0.91

Else

-0.84

spring

-0.83

ILLE

-0.79

reads

-0.78

shake

-0.77

 challeng

-0.77

reading

-0.76

Tea

-0.73

DragonMagazine

-0.72

POSITIVE LOGITS

uter

1.11

onomy

0.92

ilitarian

0.88

agonist

0.87

 Parenthood

0.79

onom

0.79

ilities

0.78

rolet

0.74

ctive

0.74

onomic

0.71

Activations Density 0.011%

terms related to legislative or regulatory actions

the term "polluter" and its variations related to environmental impact

No Comments

No Known Activations