INDEX

Explanations

template-related references in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

WebControls

-0.86

tvguidetime

-0.78

WritableDatabase

-0.78

 تضيفلها

-0.76

يميديا

-0.72

cstdio

-0.68

zeptember

-0.67

ArgsConstructor

-0.64

مصادر

-0.63

 مشين

-0.63

POSITIVE LOGITS

0.63

 land

0.51

rån

0.50

 respeito

0.49

0.47

#__

0.46

multicolumn

0.46

oa̍t

0.46

TokenName

0.45

or

0.45

Activations Density 0.022%

template-related references in code

No Comments

No Known Activations