INDEX

Explanations

phrases related to actions that happen before a specific event

oai_token-act-pair · gpt-3.5-turbo

instances of the word "before."

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

hack

-0.76

aez

-0.74

JV

-0.73

oret

-0.71

amount

-0.69

NRS

-0.69

aren

-0.69

DC

-0.67

geist

-0.66

venture

-0.65

POSITIVE LOGITS

 settling

0.81

 sunset

0.80

 fading

0.78

 embark

0.78

 realizing

0.76

 returning

0.75

 disappearing

0.75

 sunrise

0.74

 committing

0.74

piv

0.72

Activations Density 0.058%

phrases related to actions that happen before a specific event

instances of the word "before."

No Comments

No Known Activations