INDEX

Explanations

medical or technical terms

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

<bos>

-0.67

 дописавши

-0.63

bewerken

-0.57

Попис

-0.55

/***

-0.53

InstrumentedTest

-0.52

intios

-0.51

FormTagHelper

-0.51

 Wiktionnaire

-0.51

Viitteet

-0.50

POSITIVE LOGITS

Wtf

0.79

 🥲

0.79

 Lmao

0.73

 lmfao

0.72

 🤣🤣

0.71

 🙃

0.69

 😭😭

0.68

 😬

0.66

 Minang

0.66

 🤦

0.64

Activations Density 0.331%

medical or technical terms

No Comments

No Known Activations