INDEX

Explanations

references to formatting functions and XML schema definitions

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

半

-0.75

</em>

-0.61

of

-0.57

via

-0.57

diğinde

-0.57

’

-0.56

SOAP

-0.56

<u>

-0.55

<strong>

-0.55

POSITIVE LOGITS

fmt

2.05

fmt

1.89

FMT

0.98

 moulds

0.93

Fmt

0.92

 XCTest

0.91

 تضيفلها

0.90

Lähteet

0.89

 Gump

0.85

 molds

0.82

Activations Density 0.096%

references to formatting functions and XML schema definitions

No Comments

No Known Activations