INDEX

Explanations

proper nouns or names of places, products, and people

oai_token-act-pair · gpt-3.5-turbo

references to specific people, organizations, or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.66

©¶æ

-0.63

)]

-0.60

said

-0.59

Topics

-0.59

)]

-0.59

upon

-0.56

Registered

-0.56

 IMAGES

-0.55

please

-0.55

POSITIVE LOGITS

 itself

0.71

vertisement

0.69

*.

0.66

!!!!!!!!

0.65

interstitial

0.64

oooooooo

0.60

!:

0.56

().

0.54

 Incarn

0.54

Activations Density 0.946%

proper nouns or names of places, products, and people

references to specific people, organizations, or concepts

No Comments

No Known Activations