INDEX

Explanations

names and terms that begin with "Ro" or contain a repeated "ro" pattern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Grüße

-0.64

èlement

-0.59

 "..\..\..\

-0.58

 Nuevas

-0.58

onViewCreated

-0.58

 Merz

-0.57

Bronnen

-0.57

 Stä

-0.57

payee

-0.56

ImageField

-0.56

POSITIVE LOGITS

 createSlice

0.60

 Roos

0.60

 Rovers

0.60

Ro

0.57

Przypisy

0.55

tvguidetime

0.54

SBATCH

0.54

ROD

0.53

RotationOrder

0.53

contentLoaded

0.53

Activations Density 0.156%

names and terms that begin with "Ro" or contain a repeated "ro" pattern

No Comments

No Known Activations