INDEX

Explanations

references to potential outcomes or opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

XtraEditors

-0.61

Cartney

-0.54

 essentiellement

-0.52

presumably

-0.51

 principally

-0.51

ագրություններ

-0.49

 presumably

-0.49

DCC

-0.49

Cryptography

-0.49

■■

-0.49

POSITIVE LOGITS

 future

0.80

 candidates

0.78

 ujednoznacz

0.71

 harm

0.70

 candidat

0.70

ources

0.69

 sources

0.67

 FUTURE

0.67

 suitors

0.67

FUTURE

0.65

Activations Density 0.177%

references to potential outcomes or opportunities

No Comments

No Known Activations