INDEX

Explanations

numerical or coded representations, often related to data or mathematical expressions

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

Mathematical or code-related syntax

np_acts-logits-general · gemini-2.0-flash

punctuation and numbers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Италијани

-0.69

󠁿

-0.68

rupulous

-0.65

*/),

-0.64

Rhestr

-0.64

 russes

-0.64

رشف

-0.63

ennio

-0.63

 KeyError

-0.62

ِّف

-0.61

POSITIVE LOGITS

DOCTYPE

0.55

AddTagHelper

0.48

 propOrder

0.47

pos

0.46

Биография

0.44

creativecommons

0.44

dol

0.43

 AssemblyCulture

0.43

col

0.41

IMPORTED

0.41

Activations Density 1.327%

numerical or coded representations, often related to data or mathematical expressions

Mathematical or code-related syntax

punctuation and numbers

No Comments

No Known Activations