INDEX

Explanations

references to test functions and their evaluations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

aktery

-0.90

 Backbone

-0.83

клопе

-0.78

 Farina

-0.77

 snippetHide

-0.77

isNullOrEmpty

-0.75

OCITY

-0.74

kijken

-0.74

OGND

-0.74

 Mejía

-0.73

POSITIVE LOGITS

 tests

1.39

 test

1.38

 Test

1.30

 Tests

1.27

 TEST

1.27

test

1.25

Test

1.20

TEST

1.20

Tests

1.15

tests

1.13

Activations Density 0.149%

references to test functions and their evaluations in code

No Comments

No Known Activations