INDEX

Explanations

phrases indicating progression or sequences of events

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

"a" or "an" before a noun

np_acts-logits-general · gemini-2.0-flash

coming to an end

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

complexType

-0.73

RefNanny

-0.65

adaptiveStyles

-0.62

PYX

-0.59

kräf

-0.58

 propOrder

-0.57

 AssemblyProduct

-0.56

 jegy

-0.56

/**/*.

-0.55

POSITIVE LOGITS

 standstill

0.66

 minimum

0.53

EndContext

0.51

(!__

0.50

 terecht

0.48

 Minimum

0.47

 fever

0.47

 naught

0.47

 manutenzione

0.46

URLEncoder

0.46

Activations Density 0.123%

phrases indicating progression or sequences of events

"a" or "an" before a noun

coming to an end

No Comments

No Known Activations