INDEX

Explanations

references to locations and proximity to attractions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.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>

-1.06

 solidar

-0.73

 pessi

-0.72

/***

-0.71

 recipro

-0.66

 utop

-0.66

ⓧ

-0.66

lau

-0.64

 psycholog

-0.63

POSITIVE LOGITS

 déplo

1.05

 fameux

1.01

 bénéfice

0.97

 saurait

0.96

 triomphe

0.92

 réjou

0.87

 trésor

0.87

 marié

0.86

vœ

0.86

 règlement

0.85

Activations Density 0.239%

references to locations and proximity to attractions

No Comments

No Known Activations