INDEX

Explanations

HTML headers and structure indicators within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 newState

-0.65

ing

-0.65

writeString

-0.64

varargin

-0.61

ExtendWith

-0.60

imageName

-0.60

 varargin

-0.57

 maxn

-0.56

 reen

-0.56

 Amendments

-0.56

POSITIVE LOGITS

<h3>

1.55

###

0.60

<h4>

0.58

###

0.55

<sub>

0.55

<h5>

0.54

subsection

0.50

 modalités

0.50

』、

0.47

ので

0.44

Activations Density 0.066%

HTML headers and structure indicators within documents

No Comments

No Known Activations