INDEX

Explanations

questions related to the reasoning behind actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 propOrder

-0.82

 AssemblyCulture

-0.78

AddAttribute

-0.78

 itſelf

-0.76

atott

-0.73

 Vogel

-0.72

 χρόν

-0.72

 Catto

-0.71

 vuotta

-0.71

ंदीखरीदारी

-0.71

POSITIVE LOGITS

 за

1.09

За

1.00

por

0.86

Por

0.83

za

0.83

por

0.81

eper

0.78

 За

0.78

Por

0.78

 colorWith

0.76

Activations Density 0.030%

questions related to the reasoning behind actions or statements

No Comments

No Known Activations