INDEX

Explanations

references to the name "Gordon."

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

rrggbb

-0.86

XmlType

-0.83

 tartalomajánló

-0.82

Datuak

-0.81

 HasFactory

-0.81

TypedDataSet

-0.79

 Reſ

-0.79

 propOrder

-0.78

 Majefty

-0.77

 Anſ

-0.77

POSITIVE LOGITS

org

0.54

tim

0.53

 Gordon

0.52

 disappeared

0.51

cra

0.51

wi

0.48

Gordon

0.48

 regular

0.48

co

0.48

si

0.48

Activations Density 0.091%

references to the name "Gordon."

No Comments

No Known Activations