INDEX

Explanations

generic placeholder text or structures often used in programming or documentation

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

 Normdatei

-0.84

AndEndTag

-0.82

featureID

-0.80

 '\\;'

-0.78

 doInBackground

-0.76

 فريبيس

-0.75

 dAtA

-0.72

Transkript

-0.71

Obrázky

-0.70

AddTagHelper

-0.70

POSITIVE LOGITS

1.22

1.01

0.95

0.91

0.90

0.84

0.81

0.80

0.64

0.52

Activations Density 0.225%

generic placeholder text or structures often used in programming or documentation

No Comments

No Known Activations