INDEX

Explanations

computer-related terms and technical information

oai_token-act-pair · gpt-3.5-turbo

technical jargon and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olphin

-0.81

dinand

-0.78

reb

-0.76

CVE

-0.74

osponsors

-0.74

owship

-0.71

oice

-0.71

mos

-0.70

isbury

-0.66

deen

-0.66

POSITIVE LOGITS

 outline

1.13

 wording

0.98

 outlines

0.97

 summar

0.95

 condensed

0.92

 explanation

0.89

 summarize

0.88

 outlining

0.87

 gist

0.86

 exposition

0.80

Activations Density 0.236%

computer-related terms and technical information

technical jargon and terms

No Comments

No Known Activations