INDEX

Explanations

companies, names, and details related to specific organizations or events

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>

-2.77

-0.87

ⓧ

-0.83

SystemColors

-0.74

DataAnnotations

-0.71

<?

-0.69

ൊ

-0.69

 Italijani

-0.67

font

-0.67

AllowUser

-0.64

POSITIVE LOGITS

 maneu

1.81

 inev

1.61

 increa

1.55

 milano

1.54

 impra

1.53

 embra

1.52

 depic

1.52

 excru

1.51

 indestru

1.50

 emphat

1.49

Activations Density 0.184%

companies, names, and details related to specific organizations or events

No Comments

No Known Activations