INDEX

Explanations

phrases related to events or incidents

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "what happened."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arta

-0.92

mens

-0.83

hart

-0.81

ware

-0.80

reci

-0.80

hetically

-0.79

ently

-0.76

urdy

-0.74

stood

-0.73

urry

-0.72

POSITIVE LOGITS

EStream

0.84

cffffcc

0.80

 happening

0.75

 Canaver

0.75

 Ambro

0.73

 happen

0.72

 wrong

0.71

 occurring

0.71

 Hoff

0.70

 unfolding

0.70

Activations Density 0.035%

phrases related to events or incidents

instances of the phrase "what happened."

No Comments

No Known Activations