INDEX

Explanations

locations in Texas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.91

جن

-0.67

addCriterion

-0.65

América

-0.65

통

-0.62

 опо

-0.61

apnews

-0.60

 запо

-0.60

홈

-0.60

public

-0.60

POSITIVE LOGITS

TX

1.89

TX

1.76

 Telex

1.75

Tx

1.64

 stockholm

1.63

RX

1.62

 pollut

1.60

 ?...

1.59

 Intere

1.58

 wien

1.56

Activations Density 0.210%

locations in Texas

No Comments

No Known Activations