INDEX

Explanations

terms related to procedural steps and confirmations in processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 للمعارف

-1.03

 незавершена

-0.95

uxxxx

-0.77

SourceChecksum

-0.77

 Мексичка

-0.75

 ModelExpression

-0.73

 للاسماء

-0.71

Autoritní

-0.69

adə

-0.68

featureID

-0.66

POSITIVE LOGITS

 parcour

0.57

 spiral

0.54

ató

0.53

 IOError

0.53

 sánh

0.52

ductory

0.51

 secco

0.51

utation

0.51

 explanatory

0.50

 exploratory

0.49

Activations Density 0.459%

terms related to procedural steps and confirmations in processes

No Comments

No Known Activations