INDEX

Explanations

assignments or equality statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

儀

-0.67

ness

-0.63

kirch

-0.63

bub

-0.62

CommonModule

-0.62

foro

-0.60

 socc

-0.60

 المؤ

-0.59

этому

-0.59

ous

-0.59

POSITIVE LOGITS

/=

1.84

1.75

>=</

1.74

}=

1.36

.=

1.34

)=

1.34

$=

1.32

_=

1.29

]=

1.28

:=

1.28

Activations Density 0.381%

assignments or equality statements in code

No Comments

No Known Activations