INDEX

Explanations

technical information related to forums or mailing lists

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

Mhm

-0.65

enterOuterAlt

-0.62

 préférable

-0.59

<bos>

-0.56

 évident

-0.56

 kubwa

-0.55

 nzuri

-0.55

 bawat

-0.53

Obrázky

-0.53

 Rech

-0.53

POSITIVE LOGITS

 autunno

1.12

 --------------

0.96

 particolar

0.91

 tramont

0.89

 marcato

0.85

 paradiso

0.85

 incess

0.85

 divertimento

0.85

 tranquillo

0.84

 quegli

0.83

Activations Density 0.289%

technical information related to forums or mailing lists

No Comments

No Known Activations