INDEX

Explanations

references to geographical features, particularly mountains and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 interesar

-0.34

 gull

-0.31

maxcdn

-0.31

ゞ

-0.31

 Phantom

-0.30

ۜ

-0.30

adjoint

-0.30

lytic

-0.29

 oprot

-0.29

 Futebol

-0.29

POSITIVE LOGITS

 Mount

2.30

Mount

2.23

 mount

2.23

Mt

2.19

 Mont

2.06

mount

2.06

 MOUNT

2.05

MT

2.00

 mounts

1.98

mt

1.95

Activations Density 1.261%

references to geographical features, particularly mountains and related terminology

No Comments

No Known Activations

references to geographical features, particularly mountains and related terminology

No Comments

No Known Activations