INDEX

Explanations

words related to distractions and efforts to divert attention

oai_token-act-pair · gpt-3.5-turbo

terms related to distraction and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ept

-0.64

holm

-0.63

 Numbers

-0.62

iders

-0.61

fred

-0.61

anyahu

-0.60

iton

-0.60

kov

-0.60

 bloc

-0.59

 conditional

-0.59

POSITIVE LOGITS

 attention

0.80

aline

0.75

 distract

0.75

 distracting

0.73

 distractions

0.72

uyomi

0.71

icult

0.70

ingly

0.69

ibility

0.66

staff

0.65

Activations Density 0.058%

words related to distractions and efforts to divert attention

terms related to distraction and its effects

No Comments

No Known Activations