INDEX

Explanations

references to health metrics and assessments

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

Numbers surrounded by other characters

np_acts-logits-general · gemini-2.0-flash

`BeginContext` and `AndEndTag`

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

:✨

-0.91

MigrationBuilder

-0.84

Personensuche

-0.82

TintMode

-0.77

addCriterion

-0.76

-0.74

uxxxx

-0.74

 kasarigan

-0.70

CreateModel

-0.70

webElementXpaths

-0.69

POSITIVE LOGITS

AndEndTag

0.70

0.54

BeginContext

0.53

0.51

0.47

 miliki

0.47

RequestQueue

0.45

󠁮

0.45

aville

0.44

Activations Density 0.320%

references to health metrics and assessments

Numbers surrounded by other characters

`BeginContext` and `AndEndTag`

No Comments

No Known Activations