INDEX

Explanations

specific key terms or phrases related to data and technology

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

Code snippets or technical questions

np_acts-logits-general · gemini-2.0-flash

after offic Decision

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.49

 "}";

-0.49

-0.48

getAs

-0.48

 coronavirus

-0.47

 cannabis

-0.46

 marijuana

-0.46

New

-0.46

<eos>

-0.45

POSITIVE LOGITS

 propOrder

1.07

oredCriteria

0.99

SharedDtor

0.93

 Roskov

0.92

 AttributeSet

0.91

IsMutable

0.87

 protoimpl

0.86

 EconPapers

0.86

 Inflate

0.84

 noqa

0.84

Activations Density 1.857%

specific key terms or phrases related to data and technology

Code snippets or technical questions

after offic Decision

No Comments

No Known Activations