INDEX

Explanations

terms related to testing and evaluation processes

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

listdir

-0.58

ConstraintMaker

-0.55

gatsby

-0.54

rceil

-0.54

DockStyle

-0.54

Tembelea

-0.52

CodeAttribute

-0.52

astify

-0.51

יבות

-0.50

 Gogh

-0.50

POSITIVE LOGITS

 test

1.16

 testing

1.15

 Test

1.10

 tested

1.09

 tests

1.06

 experiment

1.06

 Tests

1.04

 experimented

1.02

 Testing

1.02

Test

1.02

Activations Density 0.123%

terms related to testing and evaluation processes

No Comments

No Known Activations