INDEX

Explanations

hash tags

oai_token-act-pair · gpt-3.5-turbo

references to hashtags used in social media discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ramid

-0.73

kus

-0.73

oun

-0.73

ntil

-0.69

ateral

-0.69

undai

-0.68

 trave

-0.65

artment

-0.65

 contracting

-0.65

 chambers

-0.65

POSITIVE LOGITS

 hashtag

1.26

 hasht

1.04

"#

0.98

="#

0.97

tags

0.97

=""

0.89

âĢİ

0.86

=\"

0.85

netflix

0.78

(#

0.73

Activations Density 0.011%

hash tags

references to hashtags used in social media discussions

No Comments

No Known Activations