INDEX

Explanations

terms related to medical conditions and treatments

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

kezett

-0.55

렷

-0.49

enment

-0.48

ilead

-0.47

idopsis

-0.47

 Ordner

-0.47

éhez

-0.46

kezik

-0.46

extField

-0.44

liminary

-0.43

POSITIVE LOGITS

 Augu

0.85

 Autre

0.84

 ujedno

0.81

 Leurs

0.81

 mécanisme

0.80

 transfé

0.79

 Khart

0.79

 viciss

0.77

 carrefour

0.76

 zove

0.75

Activations Density 0.225%

terms related to medical conditions and treatments

No Comments

No Known Activations