INDEX

Explanations

class and method references in programming contexts

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

Bronnen

-0.82

posedge

-0.82

verwijspagina

-0.81

DoubleQuotes

-0.80

 ModelExpression

-0.76

BeginContext

-0.75

 kasarigan

-0.73

TagMode

-0.71

djangoproject

-0.71

 становника

-0.70

POSITIVE LOGITS

util

0.57

reportWebVitals

0.53

 Vantage

0.48

core

0.44

 Yarm

0.43

 suficiente

0.43

\"></

0.42

IRL

0.42

pho

0.42

={`${

0.42

Activations Density 0.194%

class and method references in programming contexts

No Comments

No Known Activations