INDEX

Explanations

code related to variable declarations and their expected outputs in function tests

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

 Vikipedi

-0.54

 sengaja

-0.53

fr

-0.53

ToProps

-0.47

zzleHttp

-0.46

 przep

-0.46

defaultProps

-0.45

bewerken

-0.45

If

-0.44

IfNeeded

-0.43

POSITIVE LOGITS

 expected

1.02

expected

0.95

 esperado

0.85

assertEquals

0.84

 Expected

0.83

expect

0.79

 attendu

0.78

Expected

0.78

 expect

0.72

 EXPECT

0.70

Activations Density 0.124%

code related to variable declarations and their expected outputs in function tests

No Comments

No Known Activations