INDEX

Explanations

terms related to visibility or reflection in various contexts

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

Frequently

-0.38

leftarrow

-0.37

pux

-0.37

に残

-0.37

scriptcase

-0.36

alt

-0.36

 inwoners

-0.35

 tronco

-0.35

get

-0.35

 trein

-0.35

POSITIVE LOGITS

PerformLayout

1.16

 تضيفلها

0.80

Lycka

0.79

 MainAxisSize

0.74

]--;

0.74

ftagPool

0.74

httphttps

0.71

FailureListener

0.71

 AttributeSet

0.70

 itſelf

0.70

Activations Density 0.708%

terms related to visibility or reflection in various contexts

No Comments

No Known Activations

terms related to visibility or reflection in various contexts

No Comments

No Known Activations