INDEX

Explanations

phrases related to descriptions or characteristics of items or concepts, particularly in contexts of comparison or classification

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

Slavic or non-English words

np_acts-logits-general · gemini-2.0-flash

educational environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 which

-0.69

 about

-0.58

 where

-0.58

 only

-0.58

 each

-0.57

 various

-0.54

 with

-0.53

 first

-0.53

who

-0.53

 better

-0.52

POSITIVE LOGITS

 فريبيس

1.02

WriteBarrier

0.94

httphttps

0.93

 '\\;'

0.87

InitVars

0.86

aarrggbb

0.86

 /\.(

0.85

IContainer

0.84

 незавершена

0.84

 дописавши

0.83

Activations Density 0.033%

phrases related to descriptions or characteristics of items or concepts, particularly in contexts of comparison or classification

Slavic or non-English words

educational environments

No Comments

No Known Activations