INDEX

Explanations

health and medical related terms as well as categories and values in a structured format

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Примеча

-0.72

Hermoso

-0.71

Exelente

-0.69

 Souha

-0.69

Czym

-0.66

FTFY

-0.64

 Dijo

-0.64

mengg

-0.63

Dział

-0.62

Lmfao

-0.61

POSITIVE LOGITS

vns

0.79

 cance

0.76

↔

0.75

aen

0.75

 wien

0.74

 „,

0.73

 effe

0.73

 magis

0.72

lii

0.70

ohr

0.70

Activations Density 0.304%

health and medical related terms as well as categories and values in a structured format

No Comments

No Known Activations