INDEX

Explanations

comparisons between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases discussing differences in context or comparison

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

tti

-0.73

ilyn

-0.72

ccording

-0.72

everal

-0.68

PDATE

-0.66

bars

-0.65

Corn

-0.65

wind

-0.65

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.64

lynn

-0.63

POSITIVE LOGITS

 afar

0.99

 ours

0.98

 theirs

0.85

 ordinary

0.76

 scrimmage

0.75

 hers

0.74

 whence

0.74

 anywhere

0.70

 what

0.70

 parap

0.66

Activations Density 0.068%

comparisons between different entities or concepts

phrases discussing differences in context or comparison

No Comments

No Known Activations