INDEX

Explanations

terms related to legal and medical contexts

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

Välislingid

-0.50

 terbang

-0.49

 traslado

-0.49

ex

-0.49

addVertex

-0.48

 might

-0.48

argout

-0.48

 инвести

-0.47

Spectrum

-0.46

 exceptionally

-0.46

POSITIVE LOGITS

IntoConstraints

0.98

MigrationBuilder

0.76

 Roskov

0.76

AddHtmlAttribute

0.75

 AssemblyCulture

0.75

 unlock

0.73

 Theſe

0.72

UrlResolution

0.71

 Bioaccumulative

0.71

 IUPAC

0.71

Activations Density 5.655%

terms related to legal and medical contexts

No Comments

No Known Activations