INDEX

Explanations

medical terms and research-related keywords

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>

-1.86

ⓧ

-0.64

 مرئيه

-0.62

chengladbach

-0.60

 springfox

-0.60

 znaleźć

-0.58

warran

-0.56

 sikkert

-0.56

Și

-0.56

 puțin

-0.53

POSITIVE LOGITS

 utop

1.10

 umbro

0.98

 quoique

0.98

 uefa

0.96

 marte

0.95

 riviera

0.94

Ub

0.93

 Græ

0.92

 eiffel

0.92

Ueb

0.90

Activations Density 0.471%

medical terms and research-related keywords

No Comments

No Known Activations