INDEX

Explanations

identifiers and specific terms related to scientific contexts or research data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/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.23.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

 kabul

-0.37

datable

-0.36

olera

-0.36

 prolifer

-0.35

 wireType

-0.35

Personensuche

-0.35

edged

-0.35

Kof

-0.34

kas

-0.34

 Vand

-0.34

POSITIVE LOGITS

 kasarigan

0.46

AutoScaleMode

0.46

aarrggbb

0.45

ﬅ

0.45

:✨

0.45

Derp

0.43

haikusbot

0.43

aClass

0.43

 fhort

0.42

 ModelExpression

0.42

Activations Density 0.145%

identifiers and specific terms related to scientific contexts or research data

No Comments

No Known Activations