INDEX

Explanations

numerical sequences followed by specific keywords

oai_token-act-pair · gpt-3.5-turbo

references to specific numerical data and identifiers

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

pic

-0.68

 Spiel

-0.66

anwhile

-0.65

forth

-0.63

 Murdoch

-0.63

 dispers

-0.60

 Burgess

-0.59

SOURCE

-0.58

 longitudinal

-0.58

 comet

-0.58

POSITIVE LOGITS

Login

0.76

à¼

0.75

ãĥİ

0.73

Never

0.72

Prev

0.71

 Featured

0.70

ãĥ

0.69

Guest

0.68

à©

0.68

 Guest

0.68

Activations Density 0.145%

numerical sequences followed by specific keywords

references to specific numerical data and identifiers

No Comments

No Known Activations