INDEX

Explanations

terms related to liability and insurance concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

exitRule

-0.44

AddTagHelper

-0.44

enumii

-0.43

 Weih

-0.40

ValueStyle

-0.40

+#+#

-0.40

EREN

-0.39

Posi

-0.39

nsic

-0.38

uldig

-0.38

POSITIVE LOGITS

StructEnd

0.53

 المعيارى

0.51

InjectAttribute

0.48

UserScript

0.47

 estekak

0.46

Folgende

0.46

PvE

0.45

FTFY

0.43

ViewInit

0.43

NVIDIA

0.42

Activations Density 2.898%

terms related to liability and insurance concepts

No Comments

No Known Activations