INDEX

Explanations

specific nouns or subjects related to formal documents and academic 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

 aastal

-0.51

↵↵

-0.49

<eos>

-0.45

 cadeira

-0.43

.”

-0.43

own

-0.39

crollView

-0.37

 või

-0.37

cresc

-0.37

own

-0.36

POSITIVE LOGITS

 correctes

0.99

 <>",

0.89

cshtml

0.77

AxisAlignment

0.76

mergeFrom

0.75

awaiter

0.74

 internetowa

0.74

出版年

0.72

 consists

0.72

دانشنامهٔ

0.72

Activations Density 0.683%

specific nouns or subjects related to formal documents and academic contexts

No Comments

No Known Activations