INDEX

Explanations

instances of objects or things being physically described or mentioned

oai_token-act-pair · gpt-3.5-turbo

occurrences of various common nouns and phrases related to existence and presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.70

doms

-0.64

ctors

-0.63

nesses

-0.62

ocide

-0.60

anwhile

-0.60

}}}

-0.60

ivities

-0.60

=#

-0.59

rin

-0.58

POSITIVE LOGITS

 whereby

0.82

 indicating

0.74

 pertaining

0.74

 besides

0.74

 outlining

0.73

 lately

0.72

 devoted

0.71

abouts

0.71

 involving

0.69

»Ĵ

0.68

Activations Density 0.395%

instances of objects or things being physically described or mentioned

occurrences of various common nouns and phrases related to existence and presence

No Comments

No Known Activations