INDEX

Explanations

references to variable names and types in programming or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

</s>

-0.72

GeneratedMessage

-0.63

<b>

-0.60

+#+#

-0.60

expandindo

-0.56

Amal

-0.54

尽

-0.54

난

-0.53

setcounter

-0.53

mstyle

-0.53

POSITIVE LOGITS

VIAF

1.50

 VIAF

1.28

getV

1.20

 Vance

1.15

mV

1.07

VH

1.06

VH

1.06

Vle

1.03

 Vane

1.03

 Vaughn

1.03

Activations Density 1.088%

references to variable names and types in programming or mathematical contexts

No Comments

No Known Activations