INDEX

Explanations

elements related to data and values in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hskip

-0.60

okai

-0.59

plish

-0.57

::*;

-0.57

 Rory

-0.56

incere

-0.55

Rory

-0.55

 menyes

-0.54

ългария

-0.54

POSITIVE LOGITS

 defaultstate

1.03

ValueStyle

0.91

 <<<<<<<<<<<<<<

0.88

 surla

0.82

 disambiguazione

0.76

makeText

0.75

hline

0.72

Autoritní

0.71

 ExecuteAsync

0.71

Bronnen

0.69

Activations Density 0.005%

elements related to data and values in a structured format

No Comments

No Known Activations