INDEX

Explanations

terms related to predictions and predictive models

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

 DIRECTORY

-0.60

ISODE

-0.59

ioutil

-0.57

toBeTruthy

-0.56

OpenHelper

-0.56

üyük

-0.56

ChildScrollView

-0.56

aldehyde

-0.56

pointers

-0.55

hasMany

-0.54

POSITIVE LOGITS

avenir

0.63

 propOrder

0.63

 saites

0.61

PRED

0.61

 estimés

0.58

IVEREF

0.57

outcome

0.56

usehen

0.54

 سكانية

0.53

 PRED

0.53

Activations Density 0.115%

terms related to predictions and predictive models

No Comments

No Known Activations