INDEX

Explanations

terms related to semi-automated or semi-parametric concepts

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

<?

-0.59

enumii

-0.56

ValueGeneration

-0.50

pointment

-0.50

ellar

-0.50

SuppressMessage

-0.49

⎨

-0.48

 оригіналу

-0.47

acterial

-0.47

lief

-0.47

POSITIVE LOGITS

ंदीखरीदारी

0.67

__":

0.66

conductor

0.63

PhysRev

0.61

 conductors

0.59

 createState

0.57

 Hodgkin

0.56

iecie

0.56

CPtr

0.56

 JpaRepository

0.56

Activations Density 0.115%

terms related to semi-automated or semi-parametric concepts

No Comments

No Known Activations