INDEX

Explanations

family-related terms and relationships

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

хівовано

-0.36

laces

-0.33

MessageTagHelper

-0.32

lace

-0.32

 banda

-0.31

Ina

-0.31

 forhold

-0.31

 terecht

-0.31

 étoit

-0.30

 onderdeel

-0.30

POSITIVE LOGITS

InjectAttribute

0.81

GEBURTSDATUM

0.66

protoimpl

0.65

 CreateTagHelper

0.65

RenderAtEndOf

0.61

 Signalez

0.59

ніципа

0.56

RuleContext

0.56

DockStyle

0.54

AndroidJUnit

0.54

Activations Density 0.018%

family-related terms and relationships

No Comments

No Known Activations