INDEX

Explanations

programming and scripting language constructs or keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

int

-0.37

ap

-0.35

us

-0.32

-0.31

AZIONI

-0.31

 básica

-0.30

val

-0.30

ity

-0.30

ACIONAL

-0.30

use

-0.29

POSITIVE LOGITS

niſſe

1.09

ſchaft

1.08

ſicht

1.03

majánló

1.02

ロウィン

1.02

featureID

1.00

 ſind

0.99

iſchen

0.98

ſſung

0.97

iſche

0.97

Activations Density 0.154%

programming and scripting language constructs or keywords

No Comments

No Known Activations