INDEX

Explanations

programming or code-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addCriterion

-0.71

 SqlCommand

-0.54

reportWebVitals

-0.52

velocityX

-0.50

 male

-0.50

Mr

-0.50

anso

-0.49

 handsome

-0.47

handsome

-0.46

 Male

-0.46

POSITIVE LOGITS

 height

1.65

height

1.45

 Height

1.41

Height

1.39

 HEIGHT

1.36

 heights

1.34

 getHeight

1.31

HEIGHT

1.22

 tallest

1.15

getHeight

1.08

Activations Density 0.261%

programming or code-related elements

No Comments

No Known Activations