INDEX

Explanations

the presence of paragraphs and formatting elements

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

HTML paragraph tags

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 carp

-0.52

hlander

-0.47

cog

-0.47

 bast

-0.47

sm

-0.47

blu

-0.47

lon

-0.45

jaqueta

-0.45

orb

-0.45

amentals

-0.44

POSITIVE LOGITS

 informée

0.50

setVerticalGroup

0.45

principalTable

0.43

AddTagHelper

0.41

Furthermore

0.37

KommentareTeilen

0.37

UnsafeEnabled

0.37

 GenerationType

0.36

 inconnu

0.36

ApiModelProperty

0.36

Activations Density 0.038%

the presence of paragraphs and formatting elements

HTML paragraph tags

No Comments

No Known Activations