INDEX

Explanations

references to mathematical or comparative differences

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setViewName

-0.64

kloped

-0.60

argout

-0.56

 apellidos

-0.55

letic

-0.55

uspiel

-0.54

MLLoader

-0.54

 transferir

-0.53

oflavin

-0.53

exercises

-0.53

POSITIVE LOGITS

 between

0.69

 Diff

0.65

DIF

0.65

Dif

0.62

DIF

0.61

RectangleBorder

0.60

 Differences

0.60

GraphicsUnit

0.60

Differ

0.59

 differences

0.59

Activations Density 0.183%

references to mathematical or comparative differences

No Comments

No Known Activations