INDEX

Explanations

strings and characters related to data formatting and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RenderAtEndOf

-0.74

=',

-0.63

='+

-0.63

WithIOException

-0.63

SharedCtor

-0.59

>';

-0.59

==='

-0.56

ValueGenerated

-0.56

mitian

-0.56

 (‘

-0.56

POSITIVE LOGITS

 ſtate

0.78

 uſe

0.76

……"

0.73

 Cæsar

0.71

 ""){

0.68

 quæ

0.67

 houſe

0.67

#"

0.65

 Monfieur

0.65

WriteLiteral

0.65

Activations Density 0.375%

strings and characters related to data formatting and syntax

No Comments

No Known Activations