INDEX

Explanations

mentions of callbacks and demo references in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 esternos

-0.70

BeginContext

-0.67

 AssemblyProduct

-0.66

mstyle

-0.61

 насељу

-0.61

addProperty

-0.60

nextProps

-0.59

eneuve

-0.59

//

-0.59

+:+

-0.58

POSITIVE LOGITS

 callback

0.92

 demo

0.89

callback

0.76

 callbacks

0.75

TAWA

0.70

demo

0.70

 Demo

0.68

 defStyle

0.65

 démo

0.63

dip

0.63

Activations Density 0.091%

mentions of callbacks and demo references in programming contexts

No Comments

No Known Activations