INDEX

Explanations

mathematical symbols and variables typically found in equations or formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

principalTable

-0.96

 Roskov

-0.96

 nakalista

-0.93

 Paglinawan

-0.92

Viitteet

-0.87

uxxxx

-0.86

bootstrapcdn

-0.86

VERTISEMENT

-0.84

Gambas

-0.84

AsUp

-0.83

POSITIVE LOGITS

__(/*!

0.68

<b>

0.66

–

0.63

<i>

0.62

<u>

0.62

<strong>

0.55

<em>

0.53

</i>

0.51

{\

0.51

곤

0.50

Activations Density 0.330%

mathematical symbols and variables typically found in equations or formulas

No Comments

No Known Activations

mathematical symbols and variables typically found in equations or formulas

No Comments

No Known Activations