INDEX

Explanations

references and identifiers in technical documentation

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

The token "Source" and related text

np_acts-logits-general · gemini-2.0-flash

source

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Autoritní

-0.69

 numberOfRows

-0.66

XmlAccessorType

-0.66

AlterField

-0.64

autoreleasepool

-0.63

imwrite

-0.62

moveToFirst

-0.62

Discografia

-0.62

 DialogInterface

-0.62

SBATCH

-0.62

POSITIVE LOGITS

 source

1.65

 sources

1.57

 SOURCE

1.53

 Source

1.47

 Sources

1.41

sources

1.37

ource

1.35

source

1.34

Source

1.31

Sources

1.29

Activations Density 0.167%

references and identifiers in technical documentation

The token "Source" and related text

source

No Comments

No Known Activations