INDEX

Explanations

Twitter usernames preceded by "@" symbols

oai_token-act-pair · gpt-3.5-turbo

mentions of social media handles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 orche

-0.72

 Malk

-0.71

iod

-0.69

 frig

-0.65

 ordinance

-0.65

 intox

-0.63

 immersion

-0.63

 elect

-0.62

dil

-0.62

 retali

-0.61

POSITIVE LOGITS

(@

0.92

#$

0.91

username

0.88

deck

0.81

sorry

0.79

tip

0.79

usage

0.77

hello

0.76

uncle

0.75

usr

0.74

Activations Density 0.011%

Twitter usernames preceded by "@" symbols

mentions of social media handles

No Comments

No Known Activations