INDEX

Explanations

proper nouns or names of people, places, or things, particularly associated with awards, achievements, or governmental entities

oai_token-act-pair · gpt-3.5-turbo

phrases related to official awards or recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

boats

-0.76

Magikarp

-0.73

asons

-0.72

igans

-0.72

Jews

-0.71

Students

-0.71

arms

-0.70

Maps

-0.70

uits

-0.69

Links

-0.69

POSITIVE LOGITS

 latter

1.05

 dreaded

1.05

 entire

1.02

 venerable

0.97

 same

0.95

 original

0.94

 coveted

0.94

 aforementioned

0.92

 entirety

0.86

 infamous

0.84

Activations Density 0.641%

proper nouns or names of people, places, or things, particularly associated with awards, achievements, or governmental entities

phrases related to official awards or recognitions

No Comments

No Known Activations