INDEX

Explanations

references to unspecified things or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

tlere

-0.77

 arasındaki

-0.77

`/

-0.74

amerikanischer

-0.74

setViewportView

-0.73

TagHelpers

-0.72

etate

-0.72

SPONSORED

-0.72

={`/

-0.71

PerformLayout

-0.71

POSITIVE LOGITS

THING

1.39

 else

1.29

 anything

1.28

anything

1.27

Anything

1.22

 Anything

1.20

Everything

1.19

 everything

1.18

NOTHING

1.18

 Everything

1.17

Activations Density 0.054%

references to unspecified things or concepts

No Comments

No Known Activations