INDEX

Explanations

phrases containing the word "what."

oai_token-act-pair · gpt-3.5-turbo

questions or statements that inquire about outcomes or results

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

"}],"

-0.69

itsch

-0.65

ashington

-0.64

chio

-0.64

UME

-0.62

acious

-0.62

question

-0.62

riter

-0.61

pg

-0.61

ansom

-0.60

POSITIVE LOGITS

 happens

1.08

 develops

0.82

 happened

0.76

 happen

0.75

 unfolds

0.74

 happ

0.73

 shenanigans

0.70

 reaction

0.69

 fuss

0.67

 fools

0.66

Activations Density 0.074%

phrases containing the word "what."

questions or statements that inquire about outcomes or results

No Comments

No Known Activations