INDEX

Explanations

references to entrances or accuracy in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 pleaſure

-0.89

 AssemblyTitle

-0.85

hyrchwyd

-0.85

 EconPapers

-0.79

bootstrapcdn

-0.78

 ſmall

-0.78

Personendaten

-0.71

 greateſt

-0.71

 propOrder

-0.71

__':

-0.70

POSITIVE LOGITS

 accurate

0.58

 accurately

0.55

accurate

0.48

 Accurate

0.47

 careful

0.43

Accurate

0.43

interesting

0.43

 ACCUR

0.43

ced

0.41

 interesting

0.41

Activations Density 0.200%

references to entrances or accuracy in descriptions

No Comments

No Known Activations