INDEX

Explanations

terms related to data conversion processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 InputDecoration

-1.05

 spørs

-0.81

 QLabel

-0.77

SourceChecksum

-0.72

'][$

-0.70

strum

-0.70

octanol

-0.70

 grpc

-0.69

setupUi

-0.69

hibli

-0.68

POSITIVE LOGITS

 conversions

1.67

 converts

1.64

 Converts

1.63

 converter

1.56

 conversion

1.56

 Conversion

1.55

Converter

1.55

 converters

1.53

 convert

1.53

 Conversions

1.52

Activations Density 0.074%

terms related to data conversion processes

No Comments

No Known Activations