INDEX

Explanations

terms related to significant actions or impactful moments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.71

-0.67

ंदीखरीदारी

-0.65

pital

-0.62

MLLoader

-0.59

ability

-0.57

года

-0.55

-0.54

 høre

-0.53

clusal

-0.53

POSITIVE LOGITS

HEM

0.87

mable

0.85

mmm

0.82

mers

0.81

Bm

0.80

SPM

0.80

JIM

0.79

Wam

0.78

JAM

0.78

NEM

0.78

Activations Density 1.364%

terms related to significant actions or impactful moments

No Comments

No Known Activations