INDEX

Explanations

details related to diseases, infections, and viruses

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>

-3.06

tagHelperRunner

-0.78

 jsPsych

-0.77

rungsseite

-0.74

<!--

-0.70

 braccia

-0.70

EndProject

-0.69

Autoritní

-0.69

intios

-0.68

 viewWillAppear

-0.68

POSITIVE LOGITS

 reluct

1.46

 disagre

1.44

 unlaw

1.41

 affor

1.39

 impra

1.37

 impractica

1.34

 apprehen

1.32

 unwarran

1.31

 unspeak

1.29

 tolerably

1.29

Activations Density 0.787%

details related to diseases, infections, and viruses

No Comments

No Known Activations