INDEX

Explanations

questions and answers in a quiz or assessment format

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fit

-0.45

 plat

-0.40

Tempor

-0.40

Tmp

-0.40

 actually

-0.40

 Tempor

-0.40

 Philharmonic

-0.40

Cu

-0.39

결

-0.39

 صد

-0.39

POSITIVE LOGITS

tagHelperRunner

1.09

ScopeManager

0.96

UnusedPrivate

0.95

AddHtmlAttribute

0.89

 CURIAM

0.89

 kasarigan

0.85

دانشنامهٔ

0.82

 محفوظة

0.80

BeginContext

0.78

MigrationBuilder

0.78

Activations Density 0.041%

questions and answers in a quiz or assessment format

No Comments

No Known Activations