INDEX

Explanations

statements related to needs or requests in various contexts

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

InitVars

-0.42

Espèce

-0.41

noons

-0.40

rivit

-0.40

?")

-0.40

?<

-0.40

 Bias

-0.39

ách

-0.38

nant

-0.38

()")

-0.38

POSITIVE LOGITS

 esternos

0.64

 الرياضيه

0.58

новништво

0.53

 članak

0.52

EndContext

0.48

лтемелер

0.47

 Также

0.44

RenderAtEndOf

0.44

 AUSSI

0.44

setVerticalGroup

0.44

Activations Density 0.734%

statements related to needs or requests in various contexts

No Comments

No Known Activations