INDEX

Explanations

visual indicators or figures, particularly graphical representations of data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

expandindo

-0.96

saraba

-0.85

 dand

-0.84

copg

-0.82

 EClass

-0.80

 Wikimedijinoj

-0.74

windowFixed

-0.73

GraphicsUnit

-0.72

RTEE

-0.70

 ActionBar

-0.70

POSITIVE LOGITS

hline

1.91

<tr>

1.03

</h5>

0.77

hdashline

0.73

</blockquote>

0.67

</h4>

0.67

cline

0.66

</table>

0.65

</td>

0.64

</h6>

0.64

Activations Density 0.005%

visual indicators or figures, particularly graphical representations of data

No Comments

No Known Activations