INDEX

Explanations

specific names or identifiers related to individuals and entities

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

names and words ending in ive

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

webElementXpaths

-0.94

+#+#

-0.83

ftagPool

-0.81



-0.79

⟬

-0.76

ConstraintMaker

-0.76

MLLoader

-0.75

tvguidetime

-0.75

IsContent

-0.71

bootstrapcdn

-0.71

POSITIVE LOGITS

<eos>

0.54

↵↵

0.48

Réponse

0.42

↵

0.42

 Stä

0.41

0.40

0.38

0.37

Activations Density 0.008%

specific names or identifiers related to individuals and entities

names and words ending in ive

No Comments

No Known Activations