INDEX

Explanations

easy-to-use features, tools, or applications

oai_token-act-pair · gpt-3.5-turbo

instructions or suggestions for practical actions

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

yi

-0.80

sha

-0.76

nih

-0.74

bane

-0.71

Ń·

-0.70

Jer

-0.69

ĸļ

-0.69

zn

-0.69

shown

-0.69

conserv

-0.67

POSITIVE LOGITS

 setups

0.82

uate

0.76

ompl

0.70

ulate

0.68

itaire

0.66

 Adapter

0.66

 workspace

0.66

 controllers

0.65

 accompl

0.65

 multit

0.65

Activations Density 0.165%

easy-to-use features, tools, or applications

instructions or suggestions for practical actions

No Comments

No Known Activations