INDEX

Explanations

numerical data, particularly in a format related to analyses or forecasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.4.hook_mlp_out

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

WebVitals

-0.68

\{\\

-0.66

σθαι

-0.59

felves

-0.56

Demikian

-0.55

arson

-0.54

JsonInclude

-0.53

 HasFactory

-0.50

IGraphics

-0.50

anced

-0.49

POSITIVE LOGITS

ngdoc

0.63

scheme

0.55

 Converter

0.52

GroupLayout

0.50

help

0.49

 hjel

0.49

jete

0.48

tá

0.47

IVEREF

0.47

IInterface

0.47

Activations Density 0.570%

numerical data, particularly in a format related to analyses or forecasts

No Comments

No Known Activations