INDEX

Explanations

words related to images or visual content

oai_token-act-pair · gpt-3.5-turbo

terms related to media, pop culture, and fandom

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

à¨

-0.71

ollah

-0.70

ADA

-0.60

":-

-0.59

à©

-0.59

 Brow

-0.58

FINE

-0.58

 Verb

-0.57

ocene

-0.57

of

-0.57

POSITIVE LOGITS

paces

0.82

cius

0.69

pora

0.69

 wagon

0.69

 guiActiveUnfocused

0.67

 prominently

0.66

ea

0.65

 circa

0.65

seys

0.63

abilia

0.63

Activations Density 0.497%

words related to images or visual content

terms related to media, pop culture, and fandom

No Comments

No Known Activations