INDEX

Explanations

technical terms and references related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Anſ

-0.72

 auffi

-0.71

 Reſ

-0.69

 Addr

-0.68

 sandero

-0.67

 meriva

-0.64

 enfans

-0.64

 ſever

-0.63

 celta

-0.63

 Freq

-0.62

POSITIVE LOGITS

pro

0.76

 AssemblyTitle

0.75

ro

0.75

ra

0.74

co

0.73

tra

0.73

op

0.72

bra

0.71

lo

0.71

sk

0.70

Activations Density 0.356%

technical terms and references related to programming and software development

No Comments

No Known Activations