INDEX

Explanations

Twitter handles and related words

oai_token-act-pair · gpt-3.5-turbo

specific identifiers or codes, likely related to individuals or entities on social media

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

 beginners

-0.73

 Levant

-0.68

CLASSIFIED

-0.68

theless

-0.64

 shorth

-0.64

 carbohyd

-0.63

 immunity

-0.61

inarily

-0.61

upiter

-0.61

ettings

-0.60

POSITIVE LOGITS

qq

0.95

jj

0.84

ifi

0.79

ua

0.79

0.76

cz

0.75

Uk

0.75

bh

0.73

ihara

0.73

dc

0.72

Activations Density 0.051%

Twitter handles and related words

specific identifiers or codes, likely related to individuals or entities on social media

No Comments

No Known Activations