INDEX

Explanations

words related to matching or compatibility

oai_token-act-pair · gpt-3.5-turbo

instances of the word "match," specifically in contexts related to comparisons or alignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

pmwiki

-0.80

irtual

-0.77

cember

-0.70

ä¼

-0.67

################################

-0.64

umn

-0.63

Vert

-0.62

raft

-0.61

cknow

-0.61

Balt

-0.60

POSITIVE LOGITS

 matches

1.05

 match

1.00

 Match

0.85

match

0.82

 matched

0.80

ees

0.79

maker

0.76

fit

0.73

ingly

0.70

makers

0.69

Activations Density 0.016%

words related to matching or compatibility

instances of the word "match," specifically in contexts related to comparisons or alignments

No Comments

No Known Activations