INDEX

Explanations

mathematical symbols and formatting related to complex equations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

hofen

-0.85

MOC

-0.80

 Katsu

-0.78

ᾶ

-0.77

 Rankin

-0.77

DPI

-0.75

 Bernal

-0.75

fulness

-0.75

vivi

-0.74

Rul

-0.73

POSITIVE LOGITS

_{\

1.68

 }_{\

1.44

}_{\

1.33

)_{\

1.23

_{\

1.15

}}_{\

1.08

]_{\

0.98

 $_{\

0.92

\|_{\

0.87

thet

0.86

Activations Density 0.225%

mathematical symbols and formatting related to complex equations and expressions

No Comments

No Known Activations