INDEX

Explanations

terms related to evolutionary concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pertanto

-0.46

 istrinya

-0.46

 derfor

-0.44

 Derfor

-0.44

 acuer

-0.44

 gustó

-0.44

 natomiast

-0.43

 recomiendo

-0.43

 nemlig

-0.42

iertamente

-0.42

POSITIVE LOGITS

 defaultstate

0.73

 autorytatywna

0.70

setVerticalGroup

0.69

 computations

0.67

 calculations

0.64

 typing

0.62

 scheduling

0.61

ChildScrollView

0.61

 Scheduling

0.60

Scheduling

0.59

Activations Density 0.193%

terms related to evolutionary concepts

No Comments

No Known Activations