INDEX

Explanations

text that indicates the presence of specific formatting or structure in a document, particularly HTML elements or code-related tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

最快更新

-0.83

AddAttribute

-0.82

 Wickham

-0.79

 wireType

-0.78

yntaxException

-0.78

 fieldNum

-0.77

featureID

-0.76

MessageState

-0.74

HasColumnType

-0.73

achsen

-0.71

POSITIVE LOGITS

<h3>

0.76

<table>

0.75

<h2>

0.72

<h4>

0.71

<h5>

0.71

<h6>

0.68

subsection

0.67

subsubsection

0.62

Piz

0.60

 Kepler

0.60

Activations Density 0.047%

text that indicates the presence of specific formatting or structure in a document, particularly HTML elements or code-related tags

No Comments

No Known Activations