INDEX

Explanations

words related to identifying or being identified

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of making or becoming identified

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

issue

-0.68

noon

-0.67

FTWARE

-0.67

kers

-0.66

ker

-0.64

dimension

-0.64

Course

-0.64

ngth

-0.63

NOT

-0.62

Osw

-0.62

POSITIVE LOGITS

ification

1.03

ifications

0.95

ify

0.93

ifiers

0.92

ifies

0.92

ified

0.88

utical

0.86

ific

0.86

ifying

0.85

rices

0.82

Activations Density 0.022%

words related to identifying or being identified

words related to the concept of making or becoming identified

No Comments

No Known Activations