INDEX

Explanations

mentions of test suites and testing configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Portale

-0.58

migrationBuilder

-0.57

quis

-0.55

Sab

-0.53

awtextra

-0.52

于

-0.52

Архівовано

-0.51

 Alden

-0.49

Sol

-0.48

cy

-0.48

POSITIVE LOGITS

ClassName

0.86

 myſelf

0.73

 Shakspeare

0.73

className

0.72

 fevere

0.67

 leſs

0.66

 themſelves

0.65

 himſelf

0.65

 ſever

0.65

 Chriftian

0.64

Activations Density 0.195%

mentions of test suites and testing configurations

No Comments

No Known Activations