INDEX

Explanations

traffic safety signs and their meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

-1.07

parsedMessage

-1.01

ArgsConstructor

-0.96

DeleteBehavior

-0.94

abestanden

-0.94

ThroughAttribute

-0.92

 صوتيه

-0.91

 محفوظة

-0.90

SourceChecksum

-0.89

uxxxx

-0.88

POSITIVE LOGITS

 signage

0.68

 warning

0.66

 signal

0.65

 segnale

0.58

 sign

0.56

 alerting

0.55

 signaling

0.55

 guide

0.52

 σή

0.52

sign

0.51

Activations Density 0.044%

traffic safety signs and their meanings

No Comments

No Known Activations