INDEX

Explanations

instances of the word "wit"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "wit" and its variations

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

 obligated

-0.68

 predatory

-0.66

 servicing

-0.65

Ü

-0.63

 educating

-0.62

 enrollment

-0.62

 lobbying

-0.61

 tradem

-0.60

srf

-0.60

ysis

-0.59

POSITIVE LOGITS

hered

1.50

chery

1.21

glers

0.98

combe

0.91

ener

0.89

bol

0.86

chers

0.86

cher

0.84

bill

0.84

sonian

0.82

Activations Density 0.025%

instances of the word "wit"

occurrences of the word "wit" and its variations

No Comments

No Known Activations