INDEX

Explanations

expressions related to perception and evaluation of experiences

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

Preceding verbs/adjectives implying appearance

np_acts-logits-general · gemini-2.0-flash

looks like

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

 Kinds

-0.85

LIKE

-0.77

Like

-0.75

 Types

-0.74

Similar

-0.73

 Like

-0.73

unlike

-0.72

kinds

-0.72

Unlike

-0.67

Kinds

-0.66

POSITIVE LOGITS

الحياه

0.59

li

0.56

تقاوى

0.55

 lenker

0.54

lie

0.53

Visitor

0.52

fjspx

0.52

igue

0.50

LIE

0.49

Gambas

0.49

Activations Density 0.119%

expressions related to perception and evaluation of experiences

Preceding verbs/adjectives implying appearance

looks like

No Comments

No Known Activations