INDEX

Explanations

terms related to experimental results and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

PerformLayout

-0.40

NoteOnEvent

-0.39

runApp

-0.39

__()

-0.38

++;

-0.36

 propOrder

-0.35

Royce

-0.34

✭

-0.34

silien

-0.34

 planting

-0.34

POSITIVE LOGITS

 obtained

2.50

obtained

2.13

 Obtained

2.02

 obtenido

1.80

 ottenuto

1.70

 obtenu

1.69

 obtenidos

1.59

 obtain

1.55

 obten

1.53

 diperoleh

1.42

Activations Density 1.804%

terms related to experimental results and measurements

No Comments

No Known Activations