INDEX

Explanations

references to specific entities or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

StructEnd

-1.09

 AssemblyCulture

-1.06

ConstraintMaker

-1.06

 Roskov

-1.06

bootstrapcdn

-1.04

mybatisplus

-1.03

+:+

-1.03

IntoConstraints

-1.00

Datuak

-1.00

 ExecuteAsync

-1.00

POSITIVE LOGITS

te

1.08

Te

0.96

te

0.95

Te

0.92

TE

0.79

tea

0.78

teis

0.78

TE

0.78

 Jacoby

0.77

Tea

0.75

Activations Density 0.544%

references to specific entities or proper nouns

No Comments

No Known Activations