INDEX

Explanations

references to various types of tests

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

test phrases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Schar

-0.57

 corporativa

-0.56

 namorados

-0.55

phonic

-0.52

 Kron

-0.52

 femininas

-0.52

 columnName

-0.51

 casais

-0.51

 készült

-0.51

memberOf

-0.51

POSITIVE LOGITS

 test

1.73

 Test

1.54

test

1.49

Test

1.39

 TEST

1.19

 tests

1.16

 Tests

1.05

getTest

1.05

TEST

1.02

 testing

0.93

Activations Density 0.078%

references to various types of tests

test phrases

No Comments

No Known Activations