INDEX

Explanations

words related to specific names and places

oai_token-act-pair · gpt-3.5-turbo

specific letters or symbols that represent names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

etheless

-0.65

tics

-0.63

Downloadha

-0.63

warm

-0.63

uador

-0.60

 polar

-0.59

CBI

-0.59

omnia

-0.59

OC

-0.58

GST

-0.56

POSITIVE LOGITS

itzer

0.72

Department

0.70

agall

0.70

ullivan

0.69

ONSORED

0.66

ENSE

0.65

utenberg

0.64

 Andrews

0.63

 Dept

0.63

nel

0.62

Activations Density 0.184%

words related to specific names and places

specific letters or symbols that represent names or titles

No Comments

No Known Activations