INDEX

Explanations

mentions of animal-related entities or topics

oai_token-act-pair · gpt-3.5-turbo

references to animals and animal-related organizations

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

chool

-0.87

creen

-0.85

 Compton

-0.82

hips

-0.81

paces

-0.76

pring

-0.75

gaard

-0.72

ession

-0.71

lain

-0.71

jong

-0.71

POSITIVE LOGITS

 carc

0.90

 welfare

0.85

aclysm

0.83

 kingdom

0.83

Animal

0.82

 cruelty

0.81

 mammal

0.79

 animal

0.79

alogue

0.79

 species

0.79

Activations Density 0.029%

mentions of animal-related entities or topics

references to animals and animal-related organizations

No Comments

No Known Activations