INDEX

Explanations

specific formatting elements or codes commonly found in technical or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

WithIOException

-0.52

UnknownFieldSet

-0.45

GEBURTS

-0.45

WriteTagHelper

-0.41

 khai

-0.41

wohl

-0.40

OpenHelper

-0.39

ArrowToggle

-0.39

Anmerkungen

-0.38

ErrUnexpected

-0.37

POSITIVE LOGITS

出版年

0.53

 kembali

0.47

rungsseite

0.47

RegressionTest

0.43

########.

0.43

 tilbage

0.42

 Rückkehr

0.42

principalTable

0.42

Gambas

0.41

 ritorno

0.40

Activations Density 0.014%

specific formatting elements or codes commonly found in technical or programming contexts

No Comments

No Known Activations