INDEX

Explanations

references to trains and railroads

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 تضيفلها

-0.76

 nahilalakip

-0.73

 NSCoder

-0.67

ISupport

-0.65

IBOutlet

-0.62

 onPostExecute

-0.62

 AssemblyCulture

-0.62

ArgsConstructor

-0.61

 ujednoznacz

-0.60

Życiorys

-0.59

POSITIVE LOGITS

 train

4.50

 Train

4.10

 trains

3.78

Train

3.70

train

3.54

 TRAIN

3.45

 Trains

3.40

trains

3.04

Trains

3.02

TRAIN

2.94

Activations Density 0.101%

references to trains and railroads

No Comments

No Known Activations