INDEX

Explanations

syntactic structures related to function definitions and method calls in programming

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

 myſelf

-0.94

 Anſ

-0.88

tvguidetime

-0.82

 iſt

-0.81

 Diſ

-0.81

__':

-0.81

]--;

-0.80

 Soro

-0.80

 leaſt

-0.80

 Houſe

-0.79

POSITIVE LOGITS

::{

0.85

 StatefulWidget

0.66

0.58

TemporalType

0.56

toHave

0.55

0.54

<strong>

0.54

EventQueue

0.51

 hữu

0.51

 variasi

0.48

Activations Density 0.033%

syntactic structures related to function definitions and method calls in programming

No Comments

No Known Activations