INDEX

Explanations

expectations and assertions related to code functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.71

 Italijanski

-0.63

ScopeManager

-0.61

Vidite

-0.59

Whatever

-0.58

enschaften

-0.58

 return

-0.57

ifrance

-0.56

Населення

-0.55

WireFormatLite

-0.55

POSITIVE LOGITS

 tests

0.91

 test

0.84

 testing

0.81

 Tests

0.78

Test

0.76

Tests

0.76

 Test

0.74

 prueba

0.73

 tested

0.72

 Testing

0.71

Activations Density 0.100%

expectations and assertions related to code functionality

No Comments

No Known Activations