INDEX

Explanations

references to purity or untainted qualities

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

CloseOperation

-0.69

脚注の使い方

-0.69

 religieuses

-0.66

ArrowToggle

-0.66

ցված

-0.62

 يتيمه

-0.61

SceneManagement

-0.60

complexContent

-0.60

cycline

-0.59

 <<<<<<<<<<<<<<

-0.59

POSITIVE LOGITS

 pure

4.30

pure

3.92

 Pure

3.81

Pure

3.77

 PURE

3.38

PURE

2.95

 purest

2.65

 purer

2.49

纯

2.34

 purity

2.30

Activations Density 0.069%

references to purity or untainted qualities

No Comments

No Known Activations