INDEX

Explanations

phrases related to official documents and statements

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>

-2.70

<?

-0.88

ⓧ

-0.84

/**

-0.79

 &___

-0.78

-0.72

 jsPsych

-0.68

 bezeichneter

-0.67

EndGlobalSection

-0.64

Jeografia

-0.64

POSITIVE LOGITS

 milf

1.09

 wikihow

0.96

 affor

0.92

 ricardo

0.91

 disreg

0.90

 🤣🤣

0.90

 lmfao

0.90

 excru

0.89

 scrat

0.88

 verona

0.88

Activations Density 0.235%

phrases related to official documents and statements

No Comments

No Known Activations