INDEX

Explanations

uncommon prefixes and suffixes in words

oai_token-act-pair · gpt-3.5-turbo

prefixes and word stems indicating negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

abouts

-0.60

minster

-0.58

 Lambert

-0.57

 deprivation

-0.56

rices

-0.56

NCT

-0.55

 Christy

-0.55

 simulator

-0.54

 Carney

-0.54

 Barker

-0.53

POSITIVE LOGITS

akable

1.30

cedented

1.17

ailability

1.06

ailable

1.00

oppable

0.98

quished

0.96

achable

0.94

umbered

0.92

fortable

0.92

arthed

0.90

Activations Density 0.055%

uncommon prefixes and suffixes in words

prefixes and word stems indicating negation or absence

No Comments

No Known Activations