INDEX

Explanations

directional movement or positional changes

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

Directional words indicating movement

np_acts-logits-general · gemini-2.0-flash

movement into or out of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.80

LookAnd

-0.78

SequentialGroup

-0.73

 defaultstate

-0.71

StoryboardSegue

-0.70

 OFDb

-0.67

()]

-0.66

 AssemblyCulture

-0.65

AccessorTable

-0.63

eningrad

-0.61

POSITIVE LOGITS

 into

0.81

 toward

0.59

 onto

0.58

 towards

0.58

into

0.53

to

0.49

raad

0.43

enn

0.42

 INTO

0.42

wards

0.42

Activations Density 0.185%

directional movement or positional changes

Directional words indicating movement

movement into or out of

No Comments

No Known Activations