INDEX

Explanations

terms related to scanning processes or techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

getShared

-0.70

gesch

-0.64

git

-0.62

 bonnes

-0.61

 Thug

-0.61

 gameObject

-0.59

 AssemblyCulture

-0.59

 Barr

-0.59

 juego

-0.58

 dettagli

-0.58

POSITIVE LOGITS

 scan

1.83

 scanning

1.68

 SCAN

1.68

 Scan

1.61

 scans

1.56

SCAN

1.54

scan

1.50

scanning

1.49

 Scanning

1.48

 scanned

1.48

Activations Density 0.108%

terms related to scanning processes or techniques

No Comments

No Known Activations