INDEX

Explanations

Twitter handles or usernames

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

warts

-0.76

values

-0.68

suits

-0.66

laws

-0.65

lings

-0.62

etheless

-0.60

builders

-0.60

Collins

-0.59

vals

-0.58

 challengers

-0.58

POSITIVE LOGITS

qq

0.93

qqa

0.81

tsky

0.78

daq

0.76

dq

0.74

zx

0.72

UTH

0.71

ibrary

0.70

zn

0.69

icz

0.69

Activations Density 0.070%

Twitter handles or usernames

abbreviations or acronyms related to organizations or entities

No Comments

No Known Activations