INDEX

Explanations

entities and terms related to specific companies and products in various contexts

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

starting with "Mo"

np_acts-logits-general · gemini-2.0-flash

words starting with mo

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

 nakalista

-0.85

躇

-0.79

клопе

-0.72

AutoScaleMode

-0.72

sizeCache

-0.70

++]=

-0.68

 InputDecoration

-0.66

InjectAttribute

-0.65

 onCreateView

-0.64

)$/,

-0.64

POSITIVE LOGITS

 Madness

0.66

Mox

0.58

 domo

0.58

ality

0.56

mok

0.55

 Mondays

0.55

 Mayhem

0.54

wurf

0.53

 neceff

0.52

imientos

0.52

Activations Density 0.356%

entities and terms related to specific companies and products in various contexts

starting with "Mo"

words starting with mo

No Comments

No Known Activations