INDEX

Explanations

names of individuals

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-0.77

 strap

-0.69

/**

-0.67

Đối

-0.63

HasColumnType

-0.60

Ứng

-0.59

ⓧ

-0.56

র্ব

-0.56

 fund

-0.55

Ngoài

-0.55

POSITIVE LOGITS

 Brad

1.83

Brad

1.68

 brad

1.33

 overla

1.29

 effe

1.22

Juf

1.18

ftu

1.16

 habile

1.15

 casio

1.12

myn

1.12

Activations Density 0.196%

names of individuals

No Comments

No Known Activations