INDEX

Explanations

proper nouns and email addresses

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>

-3.60

ⓧ

-0.87

 AssemblyCompany

-0.77

/***

-0.72

addComponent

-0.71

قایناقلار

-0.70

protected

-0.69

HasIndex

-0.69

EndProject

-0.67

šech

-0.67

POSITIVE LOGITS

 affor

2.08

 impra

2.08

 increa

2.02

 maneu

1.92

 volunte

1.88

 reluct

1.82

 stockholm

1.81

 unlaw

1.80

 inev

1.79

 Keny

1.78

Activations Density 0.053%

proper nouns and email addresses

No Comments

No Known Activations