INDEX

Explanations

phrases related to various locations and people

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.84

<?

-0.88

/**

-0.86

ⓧ

-0.80

-0.78

<?

-0.72

حياته

-0.66

 ensure

-0.66

 protect

-0.65

 дописавши

-0.62

POSITIVE LOGITS

Van

1.31

Juf

1.30

Van

1.25

VAN

1.22

 Minang

1.19

 rafra

1.16

 délib

1.11

 ankara

1.10

 lele

1.09

 soulign

1.09

Activations Density 0.072%

phrases related to various locations and people

No Comments

No Known Activations