INDEX

Explanations

the beginning of textual sections or paragraphs in formatted documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 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

Personendaten

-0.66

FlatAppearance

-0.38

 simplifié

-0.34

 widok

-0.33

kelijkheid

-0.31

rieved

-0.30

chränk

-0.30

 AspNetCore

-0.30

 söyledi

-0.30

Descripció

-0.29

POSITIVE LOGITS

 AssemblyCulture

0.65

AndEndTag

0.60

+#+

0.57

Personensuche

0.56

SequentialGroup

0.55

 nakalista

0.54

EDEFAULT

0.54

رشف

0.54

interopRequire

0.53

expandindo

0.52

Activations Density 0.057%

the beginning of textual sections or paragraphs in formatted documents

No Comments

No Known Activations

the beginning of textual sections or paragraphs in formatted documents

No Comments

No Known Activations