INDEX

Explanations

references to online platforms offering various services related to health and personal development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 itſelf

-2.04

 myſelf

-1.97

Efq

-1.94

ſelf

-1.90

ſelves

-1.87

 ―――――

-1.87

 pleaſure

-1.85

 iſt

-1.85

 Majefty

-1.81

 themſelves

-1.80

POSITIVE LOGITS

0.96

0.92

0.91

0.90

0.87

0.86

0.83

Activations Density 0.563%

references to online platforms offering various services related to health and personal development

No Comments

No Known Activations