INDEX

Explanations

parentheses indicating explanations or additional information

oai_token-act-pair · gpt-3.5-turbo

the presence of opening parentheses in text

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

 lull

-0.74

 millenn

-0.69

 therap

-0.68

quished

-0.68

 pale

-0.68

ris

-0.66

wre

-0.66

 Lumpur

-0.66

 cyan

-0.65

 entitle

-0.65

POSITIVE LOGITS

sic

1.34

emphasis

1.29

see

1.20

possibly

1.17

...)

1.17

including

1.16

which

1.15

via

1.13

âĢ¦)

1.12

formerly

1.11

Activations Density 0.191%

parentheses indicating explanations or additional information

the presence of opening parentheses in text

No Comments

No Known Activations