INDEX

Explanations

terms related to sin or wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 correspondingly

-0.56

ſchaft

-0.55

 للاسماء

-0.54

 تعدى

-0.53

 Majefty

-0.53

日閲覧

-0.51

 occasion

-0.50

umable

-0.49

 MainAxisSize

-0.48

 Audiodateien

-0.48

POSITIVE LOGITS

sin

0.93

sin

0.67

 sins

0.65

Sin

0.65

Sin

0.60

SIN

0.55

 sinned

0.55

 sexual

0.53

Sexual

0.51

SIN

0.50

Activations Density 0.157%

terms related to sin or wrongdoing

No Comments

No Known Activations