INDEX

Explanations

references to wires and electrical connections

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 صوتيه

-0.75

 surla

-0.74

ukkah

-0.69

 rejecting

-0.69

ynb

-0.66

printStackTrace

-0.65

 нах

-0.65

Schloss

-0.65

toMatchSnapshot

-0.65

avut

-0.64

POSITIVE LOGITS

 wire

3.28

wire

3.02

 Wire

2.99

Wire

2.94

 WIRE

2.56

 wires

2.56

WIRE

2.37

wires

2.17

 Wires

2.13

 wired

1.90

Activations Density 0.057%

references to wires and electrical connections

No Comments

No Known Activations