INDEX

Explanations

references to legal terms and concepts related to liability and negligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GenerationType

-0.54

 culprits

-0.48

 passant

-0.47

 blasphemy

-0.47

urk

-0.46

жте

-0.45

Kudos

-0.45

 Fine

-0.45

 clunky

-0.45

 paltry

-0.44

POSITIVE LOGITS

 reasonably

0.95

 reaſon

0.89

 neceff

0.85

WriteTagHelper

0.84

Personensuche

0.83

ViewFeatures

0.82

ſelves

0.82

 raisonnable

0.81

 itſelf

0.80

ſelf

0.79

Activations Density 1.372%

references to legal terms and concepts related to liability and negligence

No Comments

No Known Activations