INDEX

Explanations

technical terms and code related to memory addresses and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

parsedMessage

-0.65

 lenker

-0.64

UserScript

-0.58

eningen

-0.57

 चीज़ों

-0.56

Zdroje

-0.56

contentLoaded

-0.55

 Vikipedi

-0.55

ﷺ

-0.54

openqa

-0.53

POSITIVE LOGITS

Eh

0.58

hex

0.57

FFFF

0.57

Fh

0.56

Ah

0.54

FFFFFF

0.50

FH

0.49

 FFFF

0.48

ffff

0.48

FFF

0.48

Activations Density 1.312%

technical terms and code related to memory addresses and data structures

No Comments

No Known Activations