INDEX

Explanations

references to legal cases and allegations involving discrimination or wrongful termination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Efq

-0.78

ſelves

-0.77

 themſelves

-0.69

 Jefus

-0.69

 ་་

-0.68

 dafs

-0.68

 Theſe

-0.68

 myſelf

-0.67

 ―――――

-0.67

^(@)

-0.66

POSITIVE LOGITS

 authorities

0.82

Меня

0.71

authorities

0.71

aarrggbb

0.71

 pihak

0.67

 officials

0.67

 autoridades

0.66

 they

0.64

 worden

0.64

 Меня

0.62

Activations Density 0.603%

references to legal cases and allegations involving discrimination or wrongful termination

No Comments

No Known Activations