INDEX

Explanations

attributes related to specificity and quality in various contexts

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

adjectives describing size, quality, or state

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

it

-0.39

 bowiem

-0.38

ując

-0.38

cription

-0.35

With

-0.35

Tra

-0.34

Success

-0.34

뀌

-0.33

Tra

-0.33

The

-0.33

POSITIVE LOGITS

MLLoader

0.75

OGND

0.72

 Normdatei

0.66

Personendaten

0.62

RectangleBorder

0.57

 referrerpolicy

0.56

 PeEnEo

0.56

UVWXYZ

0.55

 ujednoznacz

0.54

rungsseite

0.54

Activations Density 0.068%

attributes related to specificity and quality in various contexts

adjectives describing size, quality, or state

No Comments

No Known Activations