INDEX

Explanations

references to the Christian faith or Christian-related entities

oai_token-act-pair · gpt-3.5-turbo

references to the term "Christian" in various contexts

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

Downloadha

-0.80

æ©

-0.78

ariat

-0.77

ðĿ

-0.72

obbies

-0.71

ounge

-0.70

frames

-0.70

skirts

-0.69

handed

-0.68

hots

-0.68

POSITIVE LOGITS

 missionaries

0.92

 Bale

0.91

 theolog

0.81

 fundamentalist

0.80

 faith

0.77

 missionary

0.76

 denominations

0.76

ization

0.76

ophe

0.76

 faiths

0.74

Activations Density 0.019%

references to the Christian faith or Christian-related entities

references to the term "Christian" in various contexts

No Comments

No Known Activations