INDEX

Explanations

affirmative phrases regarding personal capability and self-improvement

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

"Self" or independently initiated actions

np_acts-logits-general · gemini-2.0-flash

self-reliance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ophageal

-0.36

 Kron

-0.31

Rah

-0.31

 megh

-0.31

kém

-0.30

 Censo

-0.30

Locked

-0.29

лит

-0.29

ANOS

-0.29

𝟸

-0.29

POSITIVE LOGITS

 self

2.13

 Self

1.75

 самостоятельно

1.69

 independently

1.69

Self

1.66

self

1.65

 самостоя

1.62

 samodziel

1.59

 SELF

1.59

 mandiri

1.56

Activations Density 0.529%

affirmative phrases regarding personal capability and self-improvement

"Self" or independently initiated actions

self-reliance

No Comments

No Known Activations