INDEX

Explanations

references to specific names or entities, particularly related to legal or criminal activities

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

 Dijo

-0.67

 Simplemente

-0.65

IZABETH

-0.61

ējās

-0.53

 rheumatism

-0.53

 overcrow

-0.53

Sigue

-0.51

 Deber

-0.51

Merhaba

-0.50

 Tampoco

-0.50

POSITIVE LOGITS

El

1.26

El

1.20

EL

1.03

el

1.00

EI

0.91

EL

0.84

Els

0.81

 Elis

0.80

 Elsie

0.78

el

0.77

Activations Density 0.085%

references to specific names or entities, particularly related to legal or criminal activities

No Comments

No Known Activations