INDEX

Explanations

references to initiatives and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Joh

-0.74

 Rowe

-0.73

fe

-0.73

ن

-0.72

fe

-0.71

field

-0.68

 mind

-0.67

Mâ

-0.66

<i>

-0.64

POSITIVE LOGITS

Portail

1.06

 kasarigan

0.93

 themſelves

0.92

henswürdigkeiten

0.90

 defaultstate

0.89

 methodName

0.88

 anhänger

0.87

adaptiveStyles

0.86

 bershka

0.85

(;;)

0.85

Activations Density 0.321%

references to initiatives and programs

No Comments

No Known Activations