INDEX

Explanations

references to additional files or supplementary materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

uminense

-0.67

SharedDtor

-0.57

glLoadIdentity

-0.56

 zwar

-0.56

yelidikan

-0.54

lgari

-0.52

Dabei

-0.51

tamanya

-0.51

homonymie

-0.51

ípio

-0.51

POSITIVE LOGITS

RegressionTest

0.93

########.

0.84

 Dernière

0.80

 Réponses

0.74

 continúas

0.73

 MainAxisSize

0.71

 Forth

0.70

 nahilalakip

0.70

 виправивши

0.69

 "..\..\

0.68

Activations Density 0.209%

references to additional files or supplementary materials

No Comments

No Known Activations