INDEX

Explanations

terminology related to actions, specifically verbs and commands

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

 referenties

-0.72

iecie

-0.72

 оригіналу

-0.67

CloseOperation

-0.64

gonic

-0.61

CodeAttribute

-0.61

GEBURTSDATUM

-0.59

Personendaten

-0.57

TestingModule

-0.57

-0.56

POSITIVE LOGITS

ings

0.85

able

0.71

ſelf

0.69

 Yourself

0.68

 myſelf

0.65

 Thine

0.63

 themſelves

0.63

 thyself

0.63

 offs

0.63

ability

0.62

Activations Density 0.718%

terminology related to actions, specifically verbs and commands

No Comments

No Known Activations