INDEX

Explanations

terms related to automated processes and self-referencing elements in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 propOrder

-0.77

 enfans

-0.73

ViewChild

-0.69

hésite

-0.68

entis

-0.66

ImageContext

-0.64

virons

-0.64

 épais

-0.63

Empereur

-0.63

Erreferentziak

-0.62

POSITIVE LOGITS

auto

0.82

Xna

0.78

fill

0.76

IntoConstraints

0.72

 auto

0.71

texttt

0.66

Fill

0.66

 fill

0.63

Auto

0.62

appcompat

0.62

Activations Density 0.031%

terms related to automated processes and self-referencing elements in programming

No Comments

No Known Activations