INDEX

Explanations

terms related to railways and trains

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

trains and locomotives

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

findpost

-0.61

httphttps

-0.59

 للاسماء

-0.48

IntoConstraints

-0.44

Referències

-0.43

 Alembic

-0.43

 leaſt

-0.41

뀝

-0.41

 PublicKey

-0.41

 Besoin

-0.40

POSITIVE LOGITS

 Train

0.56

 train

0.56

 locomotive

0.55

 Trains

0.54

 trains

0.52

 locomotives

0.52

Train

0.50

 TRAIN

0.49

Trains

0.47

trains

0.46

Activations Density 0.086%

terms related to railways and trains

trains and locomotives

No Comments

No Known Activations