INDEX

Explanations

phrases indicating quantity or limits

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

tagHelperRunner

-1.03

ScopeManager

-0.92

 houſe

-0.77

setVerticalGroup

-0.75

FormTagHelper

-0.75

 foon

-0.73

 ragaz

-0.72

 pleaſure

-0.72

Архівовано

-0.70

IUrlHelper

-0.69

POSITIVE LOGITS

 upto

0.78

upto

0.77

 hasta

0.77

Hasta

0.74

 jopa

0.73

až

0.70

hasta

0.69

 jusqu

0.69

 hingga

0.61

valbard

0.61

Activations Density 0.213%

phrases indicating quantity or limits

No Comments

No Known Activations