INDEX

Explanations

table elements in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

IUrlHelper

-0.70

AutoField

-0.58

قایناقلار

-0.56

 kasarigan

-0.55

webElementXpaths

-0.54

DMETHOD

-0.54

@"/

-0.53

 pinulongan

-0.51

("$.

-0.51

鰭

-0.51

POSITIVE LOGITS

<td>

1.25

</tr>

0.76

td

0.74

ropriate

0.59

td

0.56

<th>

0.55

TD

0.51

CDD

0.49

ậc

0.49

 cells

0.48

Activations Density 0.062%

table elements in the document

No Comments

No Known Activations