INDEX

Explanations

references to various models and classifications within scientific contexts

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

technical acronyms and short codes, particularly those related to scientific and computing domains (like LC, LF, etc.).

oai_token-act-pair · claude-3-5-haiku-20241022 Triggered by @sewoong

specific abbreviations or acronyms formatted with uppercase letters and numbers, often appearing in technical or legal contexts.

oai_token-act-pair · deepseek-r1 Triggered by @sewoong

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

•starts with L

uppercase L

No Comments

Negative Logits

Datuak

-0.70

 MainAxisSize

-0.68

WebServlet

-0.67

asteroide

-0.65

 تانيه

-0.63

 snippetHide

-0.62

intios

-0.61

AddHtmlAttribute

-0.61

MigrationBuilder

-0.60

__*/

-0.59

POSITIVE LOGITS

LM

1.51

LC

1.48

Л

1.46

LF

1.46

1.44

LH

1.44

LK

1.41

LS

1.40

LR

1.39

LP

1.39

Activations Density 1.639%

references to various models and classifications within scientific contexts

technical acronyms and short codes, particularly those related to scientific and computing domains (like LC, LF, etc.).

specific abbreviations or acronyms formatted with uppercase letters and numbers, often appearing in technical or legal contexts.

No Comments

No Known Activations