INDEX

Explanations

words related to positive attributes or features

oai_token-act-pair · gpt-3.5-turbo

instances of the word "cool" and related expressions

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

 UNITED

-0.74

riage

-0.72

 Canaver

-0.66

Reloaded

-0.66

 Examination

-0.66

glas

-0.66

ele

-0.65

ãĥĺãĥ©

-0.64

 plagued

-0.63

roit

-0.62

POSITIVE LOGITS

 cool

0.85

ness

0.85

oola

0.84

est

0.83

 breeze

0.79

 stuff

0.78

 dude

0.77

¥µ

0.76

 gadgets

0.76

lahoma

0.76

Activations Density 0.023%

words related to positive attributes or features

instances of the word "cool" and related expressions

No Comments

No Known Activations