INDEX

Explanations

symbols and formatting elements typically found in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Shand

-0.56

rouvez

-0.55

 webbplats

-0.52

čan

-0.52

XCT

-0.51

denly

-0.50

writeByte

-0.49

Datuak

-0.48

 Política

-0.48

 переписи

-0.48

POSITIVE LOGITS

HasForeignKey

0.85

\{\\

0.77

 للاسماء

0.74

DebuggerNonUser

0.69

 تضيفلها

0.64

tvguidetime

0.63

 estekak

0.62

rebbero

0.62

COUVER

0.60

Bedankt

0.57

Activations Density 0.016%

symbols and formatting elements typically found in programming or markup languages

No Comments

No Known Activations