INDEX

Explanations

terms related to parsing or processing data

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

rungsseite

-0.47

Izvori

-0.46

AddTagHelper

-0.44

 Mert

-0.42

MethodImpl

-0.41

 duly

-0.41

 Wohl

-0.39

-0.38

Personendaten

-0.38

expandindo

-0.38

POSITIVE LOGITS

pit

1.45

Pit

1.29

Pit

1.23

pit

1.23

 pits

1.13

PIT

0.98

PIT

0.94

 Pits

0.90

pits

0.90

 pitch

0.84

Activations Density 0.103%

terms related to parsing or processing data

No Comments

No Known Activations