INDEX

Explanations

specific references to medical conditions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Personendaten

-0.84

__':

-0.63

AndEndTag

-0.63

__(/*!

-0.63

 ExecuteAsync

-0.59

 GenerationType

-0.56

Jereo

-0.55

 esternos

-0.53

>--}}

-0.52

 serdecznie

-0.52

POSITIVE LOGITS

rawDesc

0.57

apunov

0.52

 newArr

0.51

AndroidJUnit

0.51

nteral

0.51

 emper

0.50

 pleaſure

0.50

Ork

0.49

 raiſ

0.49

 approach

0.49

Activations Density 1.249%

specific references to medical conditions and their consequences

No Comments

No Known Activations