INDEX

Explanations

words related to their effectiveness and complexity in various contexts

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

Adjectives describing a situation, action, or thing

np_acts-logits-general · gemini-2.0-flash

qualitative descriptor noun phrases

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 âmes

-0.79

 épaules

-0.74

 Juifs

-0.73

 vœux

-0.69

 inconvénients

-0.68

 bénéfices

-0.67

 prochaines

-0.66

 mesmos

-0.64

 lèvres

-0.64

 autorités

-0.64

POSITIVE LOGITS

ValueStyle

0.97

NameInMap

0.91

 versions

0.81

 '\\;'

0.77

 opportunities

0.76

 solutions

0.76

Koordinaten

0.76

 notions

0.75

 ideas

0.75

 circumstances

0.74

Activations Density 1.437%

words related to their effectiveness and complexity in various contexts

Adjectives describing a situation, action, or thing

qualitative descriptor noun phrases

No Comments

No Known Activations