INDEX

Explanations

phrases containing the structure "walk in the"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arians

-0.73

soever

-0.68

mania

-0.65

bryce

-0.65

uthor

-0.64

Ļ½

-0.63

 counterparts

-0.63

istas

-0.63

xxx

-0.62

%%

-0.62

POSITIVE LOGITS

 midst

1.46

 vicinity

1.15

 aftermath

1.02

 woods

1.00

 attic

0.97

 guise

0.96

 middle

0.96

 depths

0.95

 meantime

0.94

 same

0.93

Activations Density 0.403%

phrases containing the structure "walk in the"

occurrences of the word "the" within various contexts

No Comments

No Known Activations