INDEX

Explanations

expressions of doubt or uncertainty

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

following negative terms or negations

np_acts-logits-general · gemini-2.0-flash

negation and degree

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

ียบ

-0.52

 sometimes

-0.52

 might

-0.52

 simply

-0.51

 ممکن

-0.49

belongsTo

-0.49

might

-0.49

may

-0.48

simply

-0.48

Might

-0.48

POSITIVE LOGITS

 appreciably

0.86

 noticeably

0.84

 особы

0.78

 meaningfully

0.78

 особо

0.77

 much

0.76

 defaultstate

0.74

initComponents

0.73

ScopeManager

0.72

 greatly

0.72

Activations Density 0.454%

expressions of doubt or uncertainty

following negative terms or negations

negation and degree

No Comments

No Known Activations