INDEX

Explanations

phrases indicating departure or sudden action

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "off" indicating departure or movement away

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

ancial

-0.83

Export

-0.70

MX

-0.69

 teasp

-0.69

ounty

-0.68

elsius

-0.68

Gall

-0.64

olson

-0.64

ļéĨĴ

-0.63

inity

-0.63

POSITIVE LOGITS

screen

0.90

site

0.83

 pist

0.81

stage

0.79

shoot

0.78

 leash

0.77

spr

0.76

 Broadway

0.74

cffffcc

0.73

loaded

0.73

Activations Density 0.044%

phrases indicating departure or sudden action

instances of the phrase "off" indicating departure or movement away

No Comments

No Known Activations