INDEX

Explanations

instances involving the action of pulling or extracting something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pull" in various contexts

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

ibel

-0.84

esan

-0.78

merce

-0.78

voy

-0.78

brates

-0.75

afort

-0.74

esa

-0.73

SPONSORED

-0.72

apolis

-0.71

brate

-0.70

POSITIVE LOGITS

pull

1.01

 aggro

0.96

 levers

0.96

 pull

0.95

Pull

0.91

 sled

0.81

chairs

0.80

 weeds

0.77

quote

0.73

 carts

0.73

Activations Density 0.023%

instances involving the action of pulling or extracting something

instances of the word "pull" in various contexts

No Comments

No Known Activations