INDEX

Explanations

instances of specific words related to permissions and prohibitions, especially regarding the use of content for personal or commercial purposes

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>

-3.77

/***

-0.69

Kontrola

-0.67

/*++

-0.61

 nahilalakip

-0.60

بالإنجليزية

-0.59

っこう

-0.57

Vegeu

-0.56

Более

-0.56

 springfox

-0.56

POSITIVE LOGITS

 affor

1.68

 accla

1.64

 eiffel

1.63

 increa

1.58

 stockholm

1.58

 impra

1.56

 madonna

1.56

 toledo

1.56

 disagre

1.54

 reluct

1.51

Activations Density 0.199%

instances of specific words related to permissions and prohibitions, especially regarding the use of content for personal or commercial purposes

No Comments

No Known Activations