INDEX

Explanations

sequences of numbers and characters formatted like status codes or identifiers

oai_token-act-pair · gpt-3.5-turbo

numerical status updates or identifiers related to social media posts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nomine

-0.84

 DRAG

-0.64

Â¨

-0.63

 masc

-0.62

 Belt

-0.61

NRA

-0.60

 successors

-0.58

 chants

-0.58

 Vest

-0.58

lÃ©

-0.56

POSITIVE LOGITS

1.33

1.32

1.31

1.30

1.29

Activations Density 0.047%

sequences of numbers and characters formatted like status codes or identifiers

numerical status updates or identifiers related to social media posts

No Comments

No Known Activations