INDEX

Explanations

proper nouns, particularly names of people

oai_token-act-pair · gpt-3.5-turbo

mentions of specific public figures, particularly celebrities and their interactions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Droid

-0.85

 Pelosi

-0.80

Ban

-0.80

Tag

-0.79

uca

-0.79

 pesticide

-0.78

uman

-0.78

 Koen

-0.78

omon

-0.77

 subcommittee

-0.75

POSITIVE LOGITS

 James

1.56

James

1.44

 Irving

1.26

 Sirius

1.08

Sir

1.01

Gir

0.99

Ir

0.97

Hay

0.94

Sir

0.90

Hay

0.89

Activations Density 0.372%

proper nouns, particularly names of people

mentions of specific public figures, particularly celebrities and their interactions or statements

No Comments

No Known Activations