INDEX

Explanations

technical or scientific terminologies and labels related to specific categories and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

posedge

-0.51

τώ

-0.48

ülé

-0.47

찮

-0.46

 AspNetCore

-0.45

 ControllerBase

-0.44

Should

-0.43

越好

-0.43

 hvem

-0.42

Passes

-0.42

POSITIVE LOGITS

tagHelperRunner

1.00

@"/

0.93

addCriterion

0.80

 Normdatei

0.80

webElementXpaths

0.78

تفصیلات

0.75

 становника

0.73

WebElementEntity

0.71

hoeddwyd

0.70

Bis

0.69

Activations Density 2.621%

technical or scientific terminologies and labels related to specific categories and classifications

No Comments

No Known Activations