INDEX

Explanations

specific nouns or noun phrases related to various fields, possibly in a professional or academic context

oai_token-act-pair · gpt-3.5-turbo

terms associated with healthcare, agriculture, education, and community structures

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

Joined

-0.73

tyard

-0.72

-0.71

natureconservancy

-0.66

berra

-0.66

ACTED

-0.65

irlf

-0.65

Merit

-0.62

 Joined

-0.60

terness

-0.60

POSITIVE LOGITS

-,

0.63

 equivalents

0.63

.–

0.60

 datasets

0.59

 itself

0.58

centric

0.56

.-

0.55

 popul

0.55

 metadata

0.54

 duplication

0.53

Activations Density 1.220%

specific nouns or noun phrases related to various fields, possibly in a professional or academic context

terms associated with healthcare, agriculture, education, and community structures

No Comments

No Known Activations