INDEX

Explanations

instances of mathematical or statistical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Koz

-0.90

lessed

-0.80

 rhestr

-0.80

CascadeType

-0.79

ufact

-0.77

leſs

-0.77

sonder

-0.77

ressee

-0.76

poin

-0.75

 Eliz

-0.72

POSITIVE LOGITS

</sup>

1.63

</sub>

1.49

</u>

1.26

</s>

1.20

</em>

1.07

</i>

1.00

</code>

0.99

}}

0.94

}}

0.93

⁩

0.86

Activations Density 0.211%

instances of mathematical or statistical notation

No Comments

No Known Activations