INDEX

Explanations

the term "assume" and its variations, indicating assumptions made within the context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 definitivo

-0.54

browserify

-0.54

 amea

-0.54

 Frenchman

-0.53

 vulga

-0.52

mybatisplus

-0.52

 antwoord

-0.52

 singuli

-0.51

 Hyperion

-0.51

 premat

-0.51

POSITIVE LOGITS

:✨

0.84

Geplaatst

0.81

 فريبيس

0.81

 NSCoder

0.78

aarrggbb

0.73

withIdentifier

0.72

PyExc

0.71

catching

0.69



0.67

Tembelea

0.66

Activations Density 0.158%

the term "assume" and its variations, indicating assumptions made within the context

No Comments

No Known Activations