INDEX

Explanations

references to academic journal publications and their specific details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-0.75

 strerror

-0.72

^(@)

-0.70

EditPart

-0.66

 NDEBUG

-0.65

 Monfieur

-0.65

IVEREF

-0.65

σθαι

-0.64

olesale

-0.64

 fubject

-0.64

POSITIVE LOGITS

PhysRevD

1.31

PhysRevLett

0.81

AutoField

0.60

SetBool

0.53

PhysRev

0.52

ConstraintMaker

0.51

 daun

0.51

posedge

0.50

Cor

0.50

 jsPsych

0.48

Activations Density 0.249%

references to academic journal publications and their specific details

No Comments

No Known Activations