INDEX

Explanations

discussions about motorcycles and their features

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

before descriptive adjectives

np_acts-logits-general · gemini-2.0-flash

Indian context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myſelf

-0.87

 purpoſe

-0.86

 Jefus

-0.85

 themſelves

-0.84

 uſe

-0.78

 Inſ

-0.78

 himſelf

-0.77

 Majefty

-0.77

 Theſe

-0.76

 ſever

-0.76

POSITIVE LOGITS

 irrespective

0.90

 atleast

0.85

 fundas

0.82

Apart

0.81

 Bengaluru

0.80

contd

0.78

 artistes

0.76

 Owing

0.76

 erst

0.74

 spoilt

0.74

Activations Density 0.689%

discussions about motorcycles and their features

before descriptive adjectives

Indian context

No Comments

No Known Activations