INDEX

Explanations

measurements or dimensions mentioned in terms of size

oai_token-act-pair · gpt-3.5-turbo

occurrences of the preposition "in" and related locational phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

emo

-0.66

edly

-0.65

ens

-0.64

isms

-0.62

alist

-0.59

wyn

-0.59

imaru

-0.58

PASS

-0.57

roid

-0.56

selves

-0.56

POSITIVE LOGITS

 diameter

1.08

 increments

0.94

verts

0.94

versions

0.93

 total

0.92

 advance

0.91

vert

0.89

 favor

0.88

 length

0.87

 circumference

0.86

Activations Density 0.098%

measurements or dimensions mentioned in terms of size

occurrences of the preposition "in" and related locational phrases

No Comments

No Known Activations