INDEX

Explanations

terms related to brain imaging techniques and processes

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

 Souha

-0.80

 Bár

-0.77

 riviera

-0.76

 shutterstock

-0.75

 viciss

-0.73

 Adieu

-0.70

 Valentín

-0.70

 concier

-0.69

 philanth

-0.69

 kompati

-0.68

POSITIVE LOGITS

 imaging

0.74

 scans

0.64

 scan

0.61

 scanning

0.61

 images

0.60

 analysis

0.60

 microscopy

0.59

imaging

0.59

 spectroscopy

0.58

 tomography

0.56

Activations Density 0.196%

terms related to brain imaging techniques and processes

No Comments

No Known Activations