INDEX

Explanations

references to matrices in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

сылкі

-0.77

PendingIntent

-0.74

isholm

-0.73

Слу

-0.71

PERATURE

-0.69

Else

-0.69

 मौ

-0.69

 Orrell

-0.68

 Fahren

-0.68

 orale

-0.68

POSITIVE LOGITS

 matrices

2.36

 matrix

2.35

 Matrix

2.25

 MATRIX

2.09

matrix

2.07

 Matrices

2.03

Matrix

2.00

matrices

2.00

MATRIX

1.80

Matrices

1.68

Activations Density 0.085%

references to matrices in various contexts

No Comments

No Known Activations