INDEX

Explanations

references to medical procedures and specialties

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 armées

-0.47

 dolci

-0.47

 fallu

-0.46

 surpresa

-0.46

 judiciaire

-0.46

 etapas

-0.45

 salido

-0.44

 nemmeno

-0.44

 terecht

-0.44

 automatico

-0.44

POSITIVE LOGITS

aarrggbb

0.91

 Paglinawan

0.85

WebServlet

0.79

 للاسماء

0.77

CPtr

0.76

ViewById

0.70

WireFormatLite

0.70

WriteTagHelper

0.69

OGND

0.68

ImageContext

0.68

Activations Density 0.354%

references to medical procedures and specialties

No Comments

No Known Activations