INDEX

Explanations

requests for assistance or help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 AspNetCore

-0.77

sią

-0.63

PREFIX

-0.59

 Fleming

-0.58

 Metzger

-0.57

discriminator

-0.57

\}\\

-0.57

 Leeuwen

-0.56

 segment

-0.56

 Walters

-0.55

POSITIVE LOGITS

HELP

1.26

help

1.22

 HELP

1.12

 Help

1.11

 help

1.11

Help

1.09

 Hilfe

1.05

 assistance

1.05

 AssemblyCulture

1.01

Assistance

1.00

Activations Density 0.101%

requests for assistance or help

No Comments

No Known Activations