INDEX

Explanations

symbols and punctuation marks used in coding or data representation

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

audiovisuel

-0.79

󠁢

-0.74

MessageOf

-0.70

 BoxFit

-0.66

탤

-0.66

 vuitton

-0.62

expandindo

-0.62

NOPQRST

-0.61

 simplifié

-0.59

ViewFeatures

-0.59

POSITIVE LOGITS

 nakalista

0.53

↵

0.48

於

0.48

DockStyle

0.44

dze

0.44

0.43

wt

0.43

</h5>

0.43

0.42

Activations Density 0.973%

symbols and punctuation marks used in coding or data representation

No Comments

No Known Activations