INDEX

Explanations

terms related to transformation and transference processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 fidèles

-0.61

 jugé

-0.54

 giud

-0.53

findpost

-0.51

 judiciales

-0.50

 AssemblyCulture

-0.50

Paz

-0.50

 Верхов

-0.49

mobileqq

-0.49

 lâmpada

-0.49

POSITIVE LOGITS

 Trans

2.41

Trans

2.31

 TRAN

1.87

 Transform

1.79

trans

1.76

 transform

1.73

Transform

1.70

transform

1.68

TRANS

1.65

TRAN

1.62

Activations Density 0.077%

terms related to transformation and transference processes

No Comments

No Known Activations