INDEX

Explanations

terms related to scientific and technical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

slidesToShow

-0.65

 <>",

-0.64

MessageTagHelper

-0.57

IntoConstraints

-0.57

 ModelExpression

-0.57

EDEFAULT

-0.56

UserScript

-0.56

SizeMode

-0.56

ftagPool

-0.52

ertale

-0.52

POSITIVE LOGITS

 part

0.80

 separately

0.76

part

0.75

 portion

0.73

 component

0.71

 部分

0.65

 separate

0.61

Part

0.58

 bagian

0.58

 proprement

0.58

Activations Density 1.236%

terms related to scientific and technical processes

No Comments

No Known Activations