INDEX

Explanations

phrases containing instructions or notes

oai_token-act-pair · gpt-3.5-turbo

sentences or phrases that provide clarifications or additional context

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

acerb

-0.74

ONSORED

-0.72

polit

-0.69

 presided

-0.68

ridor

-0.68

 earnest

-0.67

USS

-0.67

âĢİ

-0.67

 disillusion

-0.67

egal

-0.67

POSITIVE LOGITS

you

0.99

if

0.94

 whenever

0.92

 depending

0.92

 Users

0.90

 Suppose

0.90

 disabling

0.89

 lets

0.89

 storing

0.89

allows

0.89

Activations Density 0.428%

phrases containing instructions or notes

sentences or phrases that provide clarifications or additional context

No Comments

No Known Activations