INDEX

Explanations

references to informants and the implications of their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 tege

-0.38

 AspNetCore

-0.37

pya

-0.36

ign

-0.35

 Erişim

-0.35

 Aware

-0.34

 toured

-0.34

 وتم

-0.34

選手権

-0.33

 standar

-0.33

POSITIVE LOGITS

 quæ

0.61

 ſche

0.60

 Majefty

0.60

 ſch

0.59

 houſe

0.58

:✨

0.56

 faſt

0.56

 ſtate

0.56

 pleaſure

0.54

oredCriteria

0.54

Activations Density 0.512%

references to informants and the implications of their actions

No Comments

No Known Activations