INDEX

Explanations

acronyms followed by numbers

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to episodic content and fan engagement in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

\'

-0.67

sa

-0.63

uni

-0.62

roy

-0.61

cig

-0.61

vette

-0.61

ÃŃs

-0.60

fer

-0.60

 Patterson

-0.59

mk

-0.59

POSITIVE LOGITS

 Thumbnails

0.72

ebin

0.68

 Details

0.66

 Calculator

0.64

BACK

0.62

 Removal

0.62

itionally

0.61

stals

0.60

Offline

0.60

 Conditions

0.60

Activations Density 0.494%

acronyms followed by numbers

terms and phrases related to episodic content and fan engagement in media

No Comments

No Known Activations