INDEX

Explanations

terms related to scanning and imaging technology

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

++

-0.62

QMetaType

-0.61

पया

-0.61

Datuak

-0.60

 dreapta

-0.58

 esternos

-0.56

AddAttribute

-0.55

AndroidJUnit

-0.55

 ExecuteAsync

-0.55

}\]

-0.55

POSITIVE LOGITS

 scanner

0.69

 turbo

0.67

tur

0.65

 Canvas

0.64

 scanners

0.64

CrossRef

0.63

TUR

0.62

Packard

0.62

Canvas

0.62

DockStyle

0.61

Activations Density 2.946%

terms related to scanning and imaging technology

No Comments

No Known Activations