INDEX

Explanations

data types and their respective values or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 élector

-0.65

 useStyles

-0.65

SourceChecksum

-0.64

 presenti

-0.63

ddot

-0.62

RenderAtEndOf

-0.60

fromCharCode

-0.60

 Obed

-0.59

apunov

-0.59

//

-0.59

POSITIVE LOGITS

theless

1.02

getInteger

0.93

ized

0.88

 integers

0.85

Datuak

0.82

 ་་

0.77

 Reggie

0.76

ization

0.76

 Ather

0.74

elor

0.73

Activations Density 0.088%

data types and their respective values or attributes

No Comments

No Known Activations