INDEX

Explanations

The main thing this neuron does is find information related to providing support or assistance to various individuals or groups

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

 pagkak

-0.55

underland

-0.54

 tenuta

-0.51

Preço

-0.50

 dignité

-0.49

სქოლიო

-0.48

嵩

-0.48

Largura

-0.48

 minimalis

-0.47

ביוגרפיה

-0.46

POSITIVE LOGITS

 support

1.29

 Support

1.22

support

1.18

Support

1.17

 SUPPORT

1.15

 Supports

1.13

 supports

1.10

SUPPORT

1.07

 supporting

1.03

 Supporting

0.99

Activations Density 0.121%

The main thing this neuron does is find information related to providing support or assistance to various individuals or groups

No Comments

No Known Activations