INDEX

Explanations

phrases or words related to exceeding expectations or pushing boundaries

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stretch" used 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

nect

-0.90

eer

-0.83

ellery

-0.81

eers

-0.81

alty

-0.80

*/(

-0.77

ienced

-0.76

vernment

-0.76

gencies

-0.75

ept

-0.75

POSITIVE LOGITS

 stretched

0.91

 stretches

0.81

lim

0.76

 stretch

0.76

opian

0.74

 stretching

0.70

 Afric

0.69

 Armstrong

0.68

Stretch

0.66

 furthe

0.65

Activations Density 0.023%

phrases or words related to exceeding expectations or pushing boundaries

instances of the word "stretch" used in various contexts

No Comments

No Known Activations