INDEX

Explanations

terms related to identification and identification methods

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

échal

-0.60

 Leaf

-0.57

 =====

-0.57

^(@)

-0.57

ếp

-0.56

Eta

-0.54

 Modus

-0.54

tonsoft

-0.52

acq

-0.52

 photolibrary

-0.52

POSITIVE LOGITS

 kasarigan

0.75

 GenerationType

0.65

Identyfik

0.63

<bos>

0.60

MemoryWarning

0.59

CompleteListener

0.54

Према

0.53

 HasFactory

0.52

elemField

0.49

RenderAtEndOf

0.47

Activations Density 0.221%

terms related to identification and identification methods

No Comments

No Known Activations