INDEX

Explanations

phrases related to physical objects or actions in a procedural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.86

SourceChecksum

-0.77

ViewFeatures

-0.68

rungsseite

-0.61

AnchorTagHelper

-0.58

adaptiveStyles

-0.57

AccessorTable

-0.57

 تضيفلها

-0.57

ymal

-0.57

POSITIVE LOGITS

iffance

0.67

 thereunder

0.60

olism

0.58

 médec

0.57

]='\

0.57

Schedulers

0.56

encils

0.56

nicity

0.56

 sebaik

0.56

ẨM

0.54

Activations Density 0.845%

phrases related to physical objects or actions in a procedural context

No Comments

No Known Activations