INDEX

Explanations

activities or actions related to writing and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Audiodateien

-0.84

IntoConstraints

-0.80

⎩

-0.80

IUrlHelper

-0.79

 autorytatywna

-0.73

 propOrder

-0.71



-0.70

DoubleQuotes

-0.69

 חיצוניים

-0.69

 ostavi

-0.65

POSITIVE LOGITS

 stuff

0.87

 things

0.78

0.73

 những

0.65

0.63

 people

0.62

 money

0.59

new

0.59

 those

0.57

the

0.57

Activations Density 0.582%

activities or actions related to writing and communication

No Comments

No Known Activations