INDEX

Explanations

marketing or promotional language, potentially related to books or comics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.96

ⓧ

-1.00

 intptr

-0.87

-0.86

principalColumn

-0.85

 CreateTagHelper

-0.85

HasIndex

-0.82

/**

-0.82

isContained

-0.79

AsUp

-0.78

POSITIVE LOGITS

 impra

1.64

 unspeak

1.58

 maneu

1.52

 accla

1.51

 emphat

1.48

 affor

1.48

 disreg

1.47

 reluct

1.43

 philanth

1.42

 indescri

1.41

Activations Density 0.322%

marketing or promotional language, potentially related to books or comics

No Comments

No Known Activations