INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to individuals identified as "one of" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 equival

-0.64

respective

-0.60

cats

-0.59

given

-0.59

icans

-0.53

 Provided

-0.52

gif

-0.52

 noses

-0.51

asions

-0.51

nas

-0.50

POSITIVE LOGITS

 Hundred

0.85

 hundred

0.84

of

0.73

Drive

0.73

 step

0.71

 month

0.66

esan

0.66

eenth

0.66

teenth

0.65

 kilomet

0.64

Activations Density 0.060%

proper nouns

references to individuals identified as "one of" in various contexts

No Comments

No Known Activations