INDEX

Explanations

terms related to lines or types of communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

出版年

-0.51

 domani

-0.46

munk

-0.46

gazione

-0.46

ufel

-0.46

期刊论文

-0.45

MenuInflater

-0.45

dom

-0.45

 controlado

-0.45

 Paix

-0.44

POSITIVE LOGITS

 lines

2.10

 line

2.04

 Line

1.90

 Lines

1.86

 LINE

1.79

Lines

1.77

lines

1.75

Line

1.68

 LINES

1.59

line

1.55

Activations Density 0.251%

terms related to lines or types of communication

No Comments

No Known Activations