INDEX

Explanations

terms related to responsible and proper practices in various contexts

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

 ArrayAdapter

-0.48

vni

-0.48

 weirdly

-0.47

❮

-0.47

BeginContext

-0.46

 Kessler

-0.45

 BehaviorSubject

-0.45

 phấn

-0.44

matorium

-0.44

HandlerContext

-0.43

POSITIVE LOGITS

enough

0.89

 enough

0.88

 good

0.76

 healthy

0.76

DataAnnotations

0.74

Accurate

0.70

ItemBackground

0.69

 effective

0.69

脚注の使い方

0.69

 reliable

0.69

Activations Density 0.375%

terms related to responsible and proper practices in various contexts

No Comments

No Known Activations