INDEX

Explanations

expressions of skepticism or doubt regarding self and others' opinions

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

"Care", "think", or "know" following "t"

np_acts-logits-general · gemini-2.0-flash

don't care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

GEBURTS

-0.77

Personendaten

-0.67

SourceChecksum

-0.67

DeleteBehavior

-0.66

++]

-0.66

imageshack

-0.64

 Normdatei

-0.61

featureID

-0.59

 endblock

-0.58

ChildScrollView

-0.57

POSITIVE LOGITS

 care

2.54

 cares

2.21

 Care

2.14

 cared

2.13

 CARE

1.99

care

1.97

 caring

1.89

Care

1.85

CARE

1.76

cares

1.59

Activations Density 0.230%

expressions of skepticism or doubt regarding self and others' opinions

"Care", "think", or "know" following "t"

don't care

No Comments

No Known Activations