INDEX

Explanations

references to specific locations or points in text

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

 مشين

-0.95

íncia

-0.84

DoubleQuotes

-0.82

 Maier

-0.80

culosis

-0.77

egis

-0.77

Hydra

-0.76

MMdd

-0.76

arrows

-0.76



-0.76

POSITIVE LOGITS

 spot

1.83

 SPOT

1.81

 Spot

1.80

spot

1.58

Spot

1.57

 Spots

1.54

SPOT

1.53

 spots

1.48

spots

1.42

Spots

1.18

Activations Density 0.074%

references to specific locations or points in text

No Comments

No Known Activations