INDEX

Explanations

phrases related to transformation or conversion

oai_token-act-pair · gpt-3.5-turbo

instances of the word "a" or phrases indicating transformation into something new

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

times

-0.78

enance

-0.77

agree

-0.77

alian

-0.73

alty

-0.72

acid

-0.72

books

-0.68

words

-0.68

bots

-0.68

sun

-0.66

POSITIVE LOGITS

 manageable

0.98

 profitable

0.89

 cohesive

0.86

 usable

0.85

 nightmare

0.85

 viable

0.83

 vortex

0.82

 caricature

0.82

 respectable

0.81

 lifelong

0.81

Activations Density 0.152%

phrases related to transformation or conversion

instances of the word "a" or phrases indicating transformation into something new

No Comments

No Known Activations