INDEX

Explanations

phrases related to electrical components and equipment

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.57

ⓧ

-0.56

messageInfo

-0.56

FlatAppearance

-0.52

cert

-0.51

MockBean

-0.51

FormBorderStyle

-0.51

/***

-0.51

 OMITBAD

-0.51

/**

-0.50

POSITIVE LOGITS

 Electrical

1.06

 electrical

1.03

Electrical

1.02

 fatis

1.01

electrical

1.00

 cuit

0.93

 rocher

0.89

 bandung

0.89

 ELECTRICAL

0.87

vns

0.85

Activations Density 0.306%

phrases related to electrical components and equipment

No Comments

No Known Activations