INDEX

Explanations

phrases related to communication or interaction between individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spoken."

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

Negative Logits

Protect

-0.71

Eastern

-0.65

adj

-0.62

rather

-0.60

nen

-0.59

accompanied

-0.57

Ma

-0.56

abet

-0.55

 TRANS

-0.55

NL

-0.55

POSITIVE LOGITS

nor

1.25

yet

1.07

yet

1.06

 anymore

1.04

 anywhere

1.00

 anything

0.98

 anybody

0.94

 since

0.90

 dime

0.89

any

0.88

Activations Density 0.214%

phrases related to communication or interaction between individuals

instances of the word "spoken."

No Known Activations