INDEX

Explanations

expressions or phrases where something is described or paraphrased

oai_token-act-pair · gpt-3.5-turbo

the word "it" used in various contexts

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

hift

-0.76

ppa

-0.71

IELD

-0.69

adan

-0.68

 Panama

-0.63

 Flavoring

-0.63

icial

-0.61

-0.60

ept

-0.59

 Java

-0.59

POSITIVE LOGITS

self

0.97

 bluntly

0.80

selves

0.77

chy

0.73

unes

0.72

 succinct

0.70

 mildly

0.69

anooga

0.69

 sarcast

0.68

 selves

0.68

Activations Density 0.051%

expressions or phrases where something is described or paraphrased

the word "it" used in various contexts

No Comments

No Known Activations