INDEX

Explanations

proper nouns related to people and places

oai_token-act-pair · gpt-3.5-turbo

names of individuals and locations, particularly in a context that might involve events or statements related to them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

etheless

-0.78

TBD

-0.62

.''.

-0.59

romeda

-0.57

};

-0.56

VERTISEMENT

-0.55

@@

-0.55

ECTION

-0.55

VAT

-0.54

CLS

-0.54

POSITIVE LOGITS

Jr

0.95

iewicz

0.92

heimer

0.85

 himself

0.81

aka

0.80

 died

0.78

 knew

0.77

Sr

0.77

 disappeared

0.76

 blew

0.76

Activations Density 0.379%

proper nouns related to people and places

names of individuals and locations, particularly in a context that might involve events or statements related to them

No Comments

No Known Activations