INDEX

Explanations

code snippets and metadata related to software documentation, particularly those involving annotations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

slf

-0.63

 noqa

-0.59

openqa

-0.56

 BorderRadius

-0.51

AnchorTagHelper

-0.50

Slf

-0.48

__()

-0.47

 infil

-0.46

})]

-0.46

gnore

-0.45

POSITIVE LOGITS

addCriterion

2.58

TagMode

1.72

offsetof

1.11

protoimpl

1.08

 autorytatywna

1.07

AddTagHelper

1.00

 contextLoads

0.96

awtextra

0.94

 وتسجيلات

0.93

{@

0.92

Activations Density 0.005%

code snippets and metadata related to software documentation, particularly those involving annotations and references

No Comments

No Known Activations