INDEX

Explanations

words related to entities, such as companies or organizations

oai_token-act-pair · gpt-3.5-turbo

terms related to various forms of specificity or particularity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inav

-0.97

auder

-0.78

odium

-0.76

kef

-0.74

ask

-0.72

yrinth

-0.71

ergy

-0.67

iston

-0.66

akespe

-0.66

etsk

-0.64

POSITIVE LOGITS

Peb

0.87

Pwr

0.78

-------

0.74

Hash

0.73

ful

0.69

yy

0.69

 charms

0.68

phal

0.67

 Principle

0.67

leness

0.66

Activations Density 0.030%

words related to entities, such as companies or organizations

terms related to various forms of specificity or particularity

No Comments

No Known Activations