INDEX

Explanations

phrases or clauses indicating a specific event occurring before another event

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.77

Writer

-0.69

aren

-0.69

olog

-0.69

Die

-0.68

wire

-0.66

oret

-0.66

PROV

-0.65

DC

-0.64

ENG

-0.63

POSITIVE LOGITS

 sunset

0.81

 sunrise

0.73

 committing

0.71

 realizing

0.70

 embark

0.69

 midnight

0.69

 fading

0.66

 noon

0.66

 puberty

0.66

 undergoing

0.66

Activations Density 0.060%

phrases or clauses indicating a specific event occurring before another event

occurrences of the word "before."

No Comments

No Known Activations