INDEX

Explanations

references to specific names or entities related to narratives or discussions about characters, roles, or persons in a story

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

庭

-0.47

Naissance

-0.42

juh

-0.41

iau

-0.41

di

-0.40

InBytes

-0.40

дый

-0.39

 Meadows

-0.39

fix

-0.39

stringValue

-0.39

POSITIVE LOGITS

 Jefus

0.81

PreferredItem

0.80

########.

0.79

 Theſe

0.78

 Diſ

0.76

Efq

0.76

ftagPool

0.75

المكان

0.75

ViewFeatures

0.74

RegressionTest

0.73

Activations Density 0.099%

references to specific names or entities related to narratives or discussions about characters, roles, or persons in a story

No Comments

No Known Activations