INDEX

Explanations

references to mold and various associated health risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

λογία

-0.61

 raisonnable

-0.60

 ProtoMessage

-0.56

 légitime

-0.54

 Theſe

-0.52

 reasonably

-0.52

ละ

-0.49

الحياه

-0.49

 toer

-0.49

 rilass

-0.49

POSITIVE LOGITS

 ModelExpression

0.69

 swept

0.66

 FormGroup

0.65

SOUNDBITE

0.62

 mold

0.62

TemporalType

0.62

Lan

0.61

bibitem

0.60

 ResponseEntity

0.60

 tiger

0.59

Activations Density 2.039%

references to mold and various associated health risks

No Comments

No Known Activations