INDEX

Explanations

terms related to scientific measurements and classifications

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

tokens characteristic of technical or structured text—especially title-like key terms, hyphenated or underscored compounds, and code/citation punctuation and numbering.

oai_token-act-pair · gpt-5 Triggered by @arielgoldsteinlab

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

})_{

-0.53

\|^{

-0.51

 bezeichneter

-0.50

ardized

-0.49

ented

-0.49

 جر

-0.49

uzzy

-0.48

\}^{

-0.47

corporated

-0.46

arked

-0.46

POSITIVE LOGITS

Personendaten

0.83

RenderAtEndOf

0.82

localctx

0.71

 ویکی‌پدیا

0.69

stdc

0.65

Бахар

0.62

 BrowserModule

0.62

 onCreateView

0.61

NgModule

0.60

 resourceCulture

0.59

Activations Density 2.116%

terms related to scientific measurements and classifications

tokens characteristic of technical or structured text—especially title-like key terms, hyphenated or underscored compounds, and code/citation punctuation and numbering.

No Comments

No Known Activations