INDEX

Explanations

terms related to capacity and its various dimensions or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writeln

-0.37

 astore

-0.37

 Wör

-0.36

 Monfieur

-0.36

 Schrifts

-0.36

liyor

-0.36

VERTIS

-0.36

println

-0.36

 Chri

-0.35

ırken

-0.35

POSITIVE LOGITS

 capacity

2.36

 Capacity

2.30

Capacity

2.23

capacity

2.19

 CAPACITY

2.11

CAPACITY

1.88

 capacities

1.88

 kapac

1.66

 kapasitas

1.60

 capacidad

1.50

Activations Density 0.090%

terms related to capacity and its various dimensions or implications

No Comments

No Known Activations