INDEX

Explanations

numerical values related to minimums and maximums in data sets

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

"Minimum" or "maximum" followed by a value

np_acts-logits-general · gemini-2.0-flash

minimum or maximum values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 مشين

-0.69

 فريبيس

-0.65

 otomatig

-0.64

IndentedString

-0.62

protoimpl

-0.62

///</

-0.60

åt

-0.57

PyExc

-0.55

󠁢

-0.54

 مرئيه

-0.52

POSITIVE LOGITS

 achievable

0.87

 attainable

0.82

 possible

0.77

 value

0.76

值

0.74

 POSSIBLE

0.70

possible

0.67

 achieved

0.65

 attained

0.63

 ever

0.63

Activations Density 0.477%

numerical values related to minimums and maximums in data sets

"Minimum" or "maximum" followed by a value

minimum or maximum values

No Comments

No Known Activations