INDEX

Explanations

dialogue and quotes within the text

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

Follows quotations or interjections

np_acts-logits-general · gemini-2.0-flash

quotation marks followed by words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 فريبيس

-0.68

 utafitiHapana

-0.63

AutoScaleMode

-0.57

CppMethod

-0.57

*/].

-0.57

tbh

-0.57

autant

-0.56

aimerais

-0.56

caring

-0.55

enumi

-0.55

POSITIVE LOGITS

 here

0.78

 ready

0.69

here

0.68

 сюда

0.66

 Here

0.65

 Attention

0.63

Attention

0.62

Here

0.62

0.61

 Come

0.61

Activations Density 0.126%

dialogue and quotes within the text

Follows quotations or interjections

quotation marks followed by words

No Comments

No Known Activations