INDEX

Explanations

references to various types of wires and their organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Personensuche

-0.80

довлет

-0.73

ArgumentParser

-0.70

çalves

-0.67

onames

-0.64

pleaños

-0.64

tvguidetime

-0.64

 Muda

-0.63

msc

-0.63

 Schon

-0.63

POSITIVE LOGITS

 wire

3.06

wire

2.85

 Wire

2.77

Wire

2.67

 wires

2.54

 WIRE

2.47

WIRE

2.32

wires

2.12

 Wires

2.04

 wired

1.86

Activations Density 0.070%

references to various types of wires and their organization

No Comments

No Known Activations

references to various types of wires and their organization

No Comments

No Known Activations