INDEX

Explanations

phrases related to communication and giving instructions

oai_token-act-pair · gpt-3.5-turbo

instances of direct speech or reported dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

aghd

-0.72

oshenko

-0.71

idates

-0.69

ses

-0.61

 exploits

-0.61

 controversies

-0.60

obos

-0.57

ãĥ³

-0.57

 operates

-0.56

¥µ

-0.56

POSITIVE LOGITS

 myself

1.96

my

1.50

 mine

1.03

MY

0.88

yss

0.85

My

0.77

 ourselves

0.75

oan

0.73

him

0.73

my

0.72

Activations Density 0.446%

phrases related to communication and giving instructions

instances of direct speech or reported dialogue

No Comments

No Known Activations