INDEX

Explanations

references to dogs and related concepts

oai_token-act-pair · gpt-3.5-turbo

references to dogs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

éĹĺ

-0.87

artz

-0.79

esson

-0.79

DERR

-0.75

 Edison

-0.75

oulos

-0.74

erences

-0.74

farious

-0.73

ORN

-0.73

itures

-0.72

POSITIVE LOGITS

 barking

1.03

patch

1.03

fighting

0.98

fight

0.97

meat

0.97

fights

0.94

matically

0.94

fighter

0.94

matic

0.93

gie

0.92

Activations Density 0.036%

references to dogs and related concepts

references to dogs

No Comments

No Known Activations