INDEX

Explanations

code snippets or technical commands

oai_token-act-pair · gpt-3.5-turbo

words and phrases associated with intricate food descriptions and medical terms

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

ccording

-0.75

 reluct

-0.63

 wiser

-0.62

 inher

-0.59

 architects

-0.57

swick

-0.57

OHN

-0.55

 demographics

-0.55

actionDate

-0.54

everal

-0.54

POSITIVE LOGITS

!.

0.85

!".

0.71

!,

0.70

().

0.67

LLP

0.64

("

0.63

*.

0.63

etc

0.62

 Syndrome

0.62

locks

0.62

Activations Density 0.805%

code snippets or technical commands

words and phrases associated with intricate food descriptions and medical terms

No Comments

No Known Activations