INDEX

Explanations

key actions and processes related to achievements and collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ReusableCell

-0.59

󠁢

-0.52

ophone

-0.52

igshid

-0.48

 numerus

-0.48

 ELSE

-0.47

 continuant

-0.47

disambiguation

-0.47

 Tent

-0.47

λαν

-0.47

POSITIVE LOGITS

<bos>

3.17

the

0.66

0.55

The

0.49

/*

0.47

’

0.46

and

0.45

__':

0.45

/**

0.43

Activations Density 52.235%

key actions and processes related to achievements and collaboration

No Comments

No Known Activations