INDEX

Explanations

references to fixed properties or parameters related to stability in various contexts

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

"fixed"

np_acts-logits-general · gemini-2.0-flash

fixed

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

 AssemblyProduct

-0.87

 <<<<<<<<<<<<<<

-0.84

 Geraadpleegd

-0.76

 Administrativna

-0.75

 poffible

-0.74

 leaſt

-0.74

 Италијани

-0.73

DockStyle

-0.73

Efq

-0.73

^@

-0.72

POSITIVE LOGITS

Fix

0.93

Fix

0.93

fix

0.91

fix

0.89

FIX

0.86

FIX

0.83

 fixes

0.78

fixes

0.77

Fixes

0.72

 Fixing

0.68

Activations Density 0.104%

references to fixed properties or parameters related to stability in various contexts

"fixed"

fixed

No Comments

No Known Activations