INDEX

Explanations

phrases prompting action or engagement, often starting with the word "Find."

oai_token-act-pair · gpt-3.5-turbo

phrases that encourage action or participation

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

panic

-0.73

 fracturing

-0.68

forming

-0.63

adding

-0.62

piring

-0.62

WARNING

-0.60

slow

-0.60

idium

-0.60

 Reboot

-0.60

rising

-0.60

POSITIVE LOGITS

ById

0.93

out

0.89

 fault

0.84

 loopholes

0.84

 yourself

0.78

 ways

0.76

lay

0.74

 clues

0.74

abilia

0.74

 oneself

0.70

Activations Density 0.080%

phrases prompting action or engagement, often starting with the word "Find."

phrases that encourage action or participation

No Comments

No Known Activations