INDEX

Explanations

references to the name "Lewis" and related exhibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 HasFactory

-0.92

AndroidJUnit

-0.74

AsUp

-0.73

 endwhile

-0.70

 onCreateView

-0.70

 utafitiHapana

-0.69

IUrlHelper

-0.67

+#+#

-0.67

 Италијани

-0.66

excellents

-0.65

POSITIVE LOGITS

LOGGER

0.81

logger

0.79

LOG

0.78

Api

0.74

API

0.71

log

0.69

 agencies

0.62

LogUtil

0.61

API

0.61

Log

0.61

Activations Density 0.143%

references to the name "Lewis" and related exhibitions

No Comments

No Known Activations