INDEX

Explanations

elements related to user actions or interactions in a digital context, particularly focusing on verbs and actions that imply user engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 Brind

-0.62

einander

-0.59

ablon

-0.59

leyeb

-0.59

 mold

-0.57

::{

-0.56

മാ

-0.55

 Hodg

-0.55

enumi

-0.54

uldade

-0.54

POSITIVE LOGITS

-------------</

0.90

 مرئيه

0.86

ίνεται

0.84

 AssemblyVersion

0.79

isSuccessful

0.76

 Infórmanos

0.75

ChildScrollView

0.75

 presentarse

0.74

migrationBuilder

0.73

UnsafeEnabled

0.72

Activations Density 0.012%

elements related to user actions or interactions in a digital context, particularly focusing on verbs and actions that imply user engagement

No Comments

No Known Activations