INDEX

Explanations

code snippets or programming-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AsUp

-0.91

featureID

-0.80

XmlAccessType

-0.78

InitVars

-0.74

 ddelweddau

-0.74

Filmographie

-0.72

новниш

-0.69

SerializedSize

-0.68

HasBeenSet

-0.66

WritableDatabase

-0.66

POSITIVE LOGITS

enumi

0.52

chiali

0.46

 näh

0.45

 Zufall

0.44

></

0.42

0.41

 متعلقه

0.41

*}{

0.40

latego

0.40

 biografias

0.40

Activations Density 0.201%

code snippets or programming-related elements

No Comments

No Known Activations