INDEX

Explanations

phrases related to actions or transgressions and their consequences

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.52

Controllo

-0.52

 stihl

-0.45

ugier

-0.45

Personensuche

-0.45

Warmly

-0.45

sya

-0.45

 sensibili

-0.43

Xoxo

-0.43

 \%$\\

-0.43

POSITIVE LOGITS

now

1.22

now

1.10

Now

1.06

Now

0.97

NOW

0.92

NOW

0.89

 ahora

0.82

 lately

0.77

 nowadays

0.77

 agora

0.75

Activations Density 0.428%

phrases related to actions or transgressions and their consequences

No Comments

No Known Activations

phrases related to actions or transgressions and their consequences

No Comments

No Known Activations