INDEX

Explanations

phrases related to important, primary, or significant aspects

oai_token-act-pair · gpt-3.5-turbo

key terms and indicators related to importance and significance

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

paio

-0.96

azel

-0.84

fy

-0.80

avan

-0.77

arsh

-0.77

attery

-0.75

forms

-0.73

ork

-0.73

aping

-0.73

erved

-0.73

POSITIVE LOGITS

 reason

0.91

 culprit

0.90

iest

0.87

 difference

0.86

 exception

0.82

 objective

0.82

 theme

0.80

 proponent

0.79

 antidote

0.79

 drawback

0.77

Activations Density 0.272%

phrases related to important, primary, or significant aspects

key terms and indicators related to importance and significance

No Comments

No Known Activations