INDEX

Explanations

instances of individuals expressing opinions or remarks in a discussion or report

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

theilung

-0.50

']='

-0.47

 subject

-0.47

subject

-0.45

Ekster

-0.44

 tema

-0.44

QMetaType

-0.44

ждый

-0.44

símbolo

-0.43

 Münch

-0.43

POSITIVE LOGITS

 disambiguazione

0.75

IUrlHelper

0.70

HtmlAttribute

0.65

verwijspagina

0.65

InstrumentedTest

0.64

Gön

0.63

findpost

0.62

MemoryWarning

0.61

دانشنامهٔ

0.61

Abit

0.60

Activations Density 0.073%

instances of individuals expressing opinions or remarks in a discussion or report

No Comments

No Known Activations