INDEX

Explanations

references to significant individuals named Steve

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

-0.67

-0.57

-0.56

and

-0.54

-0.53

-0.52

-0.51

-0.49

 addition

-0.49

and

-0.49

POSITIVE LOGITS

 مشين

1.13

rungsseite

1.08

 ModelExpression

1.08

 raiſ

1.07

 ſte

1.03

 BoxFit

1.00

 protoimpl

1.00

Hauptartikel

1.00

providedIn

0.99

 للاسماء

0.98

Activations Density 0.192%

references to significant individuals named Steve

No Comments

No Known Activations