INDEX

Explanations

phrases or acronyms related to "SL" followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to regulatory or licensing frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ria

-0.72

nor

-0.69

flies

-0.66

tis

-0.66

geons

-0.66

akuya

-0.64

lies

-0.63

ãĥ£

-0.62

lia

-0.60

rians

-0.60

POSITIVE LOGITS

OTUS

0.92

ibrary

0.91

avery

0.90

ength

0.90

IDES

0.89

OOK

0.88

OTS

0.87

ASH

0.86

UT

0.84

OCK

0.84

Activations Density 0.034%

phrases or acronyms related to "SL" followed by a number

references to regulatory or licensing frameworks

No Comments

No Known Activations