INDEX

Explanations

references to railway stations and associated terminology

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

qrstuvwxyz

-0.64

WriteTagHelper

-0.62

strator

-0.61

SCAPE

-0.60

argb

-0.59

 Grecs

-0.58

 Dorado

-0.56

 corrig

-0.56

 Mandy

-0.56

likace

-0.56

POSITIVE LOGITS

 trains

1.46

 railway

1.42

 train

1.40

 Train

1.36

 Trains

1.34

Trains

1.33

 railways

1.31

 Rail

1.31

 railroad

1.31

 rail

1.30

Activations Density 0.154%

references to railway stations and associated terminology

No Comments

No Known Activations