INDEX

Explanations

adjectives indicating a high level of quality or status

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

high followed by noun/adjective

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

opsis

-0.46

PKG

-0.46

 AssemblyProduct

-0.45

amante

-0.44

tpl

-0.43

ucle

-0.42

etta

-0.42

 tablecloth

-0.41

aceae

-0.41

theless

-0.40

POSITIVE LOGITS

 High

1.13

High

1.07

 HIGH

0.99

 high

0.95

high

0.92

HIGH

0.92

Low

0.72

高

0.70

Low

0.69

高

0.69

Activations Density 0.079%

adjectives indicating a high level of quality or status

high followed by noun/adjective

No Comments

No Known Activations