INDEX

Explanations

references to specific locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 disponibilités

-0.70

 Blackstone

-0.69

GTC

-0.67

𝘅

-0.66

 Retriever

-0.65

substack

-0.65

 Lutz

-0.65

MatButtonModule

-0.64

 Kron

-0.63

THON

-0.63

POSITIVE LOGITS

 Galli

0.81

 Woodrow

0.78

 Galveston

0.76

 Cupid

0.75

Mith

0.75

 Mith

0.75

/>";

0.75

 Mahomet

0.75

 Samoa

0.74

 Samo

0.74

Activations Density 2.887%

references to specific locations and names

No Comments

No Known Activations