INDEX

Explanations

phrases related to Twitter handles

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and usernames, typically associated with social media

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

 plague

-0.88

 mandate

-0.87

 spir

-0.86

 subpoena

-0.86

 prescribed

-0.83

 warrant

-0.82

 stem

-0.81

 snowball

-0.81

 outset

-0.80

tug

-0.80

POSITIVE LOGITS

Machine

1.66

Stud

1.65

Games

1.59

Air

1.59

Gaming

1.59

Official

1.58

Party

1.58

Rules

1.58

Jr

1.58

Human

1.58

Activations Density 0.222%

phrases related to Twitter handles

proper nouns, specifically names and usernames, typically associated with social media

No Comments

No Known Activations