INDEX

Explanations

instances of the word "at" in various contexts

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

Following the word "at"

np_acts-logits-general · gemini-2.0-flash

specific points or times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 resourceCulture

-0.69

 AssemblyCulture

-0.60

 frattempo

-0.55

 actualidad

-0.55

 wireType

-0.54

GEBURTSDATUM

-0.54

addCriterion

-0.54

AndEndTag

-0.53

TagHelpers

-0.53

 Roskov

-0.53

POSITIVE LOGITS

ino

0.70

 opportune

0.59

 inconvenient

0.57

 Exactos

0.56

;</

0.56

 critical

0.56

 crucial

0.56

.},

0.55

key

0.55

 weird

0.55

Activations Density 0.191%

instances of the word "at" in various contexts

Following the word "at"

specific points or times

No Comments

No Known Activations