INDEX

Explanations

terms related to legal and ethical standards

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

 Anſ

-0.73

 chrétien

-0.73

 Chriftian

-0.71

 Majefty

-0.70

 Jefus

-0.70

Efq

-0.69

 ApiException

-0.69

 autorytatywna

-0.69

 avoient

-0.69

 Monfieur

-0.67

POSITIVE LOGITS

ble

0.76

spo

0.74

sk

0.71

sk

0.69

SC

0.69

sco

0.68

spo

0.66

sc

0.65

 scanner

0.64

sc

0.64

Activations Density 2.489%

terms related to legal and ethical standards

No Comments

No Known Activations