INDEX

Explanations

terms related to incentives and rewards 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Skocz

-0.50

UML

-0.48

 veille

-0.45

Kec

-0.44

 tombé

-0.44

annica

-0.43

 défend

-0.43

 resté

-0.40

 Récup

-0.40

 useNavigate

-0.40

POSITIVE LOGITS

 incentives

0.88

incenti

0.81

 incentive

0.81

Incenti

0.77

 Incentives

0.76

AndEndTag

0.71

 RouterModule

0.70

MergeFrom

0.67

 resourceCulture

0.67

 يتيمه

0.66

Activations Density 0.433%

terms related to incentives and rewards in various contexts

No Comments

No Known Activations