INDEX

Explanations

references to explanations or introductions

oai_token-act-pair · gpt-3.5-turbo

transitional phrases and instructions for guiding discussions or analyses

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

utm

-0.77

lees

-0.72

ald

-0.71

iao

-0.61

soever

-0.60

liam

-0.60

 Orche

-0.59

installed

-0.59

HAM

-0.59

ebook

-0.59

POSITIVE LOGITS

 primer

0.95

 basics

0.94

 definitions

0.84

 ourselves

0.81

 nutshell

0.81

Background

0.79

 specifics

0.78

 backstory

0.78

 recap

0.76

GROUND

0.73

Activations Density 0.286%

references to explanations or introductions

transitional phrases and instructions for guiding discussions or analyses

No Comments

No Known Activations