INDEX

Explanations

phrases related to online searching and sharing of ideas or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.82

 ſche

-0.81

 Reſ

-0.79

 ſtate

-0.71

 houſe

-0.69

 Majefty

-0.69

 ſever

-0.69

 raiſ

-0.68

 diſt

-0.68

 pleaſure

-0.67

POSITIVE LOGITS

www

0.95

 http

0.87

www

0.77

 https

0.69

 Amazon

0.68

 tirer

0.67

 sites

0.67

http

0.65

 сайта

0.63

 sitios

0.62

Activations Density 0.330%

phrases related to online searching and sharing of ideas or information

No Comments

No Known Activations