INDEX

Explanations

words related to marketing and promotion

oai_token-act-pair · gpt-3.5-turbo

terms related to publicity and hype

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

tein

-0.83

arre

-0.70

radical

-0.64

WER

-0.63

tre

-0.63

REE

-0.62

artment

-0.61

sonian

-0.61

abus

-0.57

cible

-0.57

POSITIVE LOGITS

 bestowed

1.07

seekers

0.99

 fades

0.98

 surrounding

0.94

 afforded

0.93

 seekers

0.90

 stunts

0.88

seeking

0.87

 tremend

0.85

 endorsements

0.83

Activations Density 0.129%

words related to marketing and promotion

terms related to publicity and hype

No Comments

No Known Activations