INDEX

Explanations

words related to comedy or comedic elements

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>

-1.57

HasIndex

-0.66

HasForeignKey

-0.60

<?

-0.56

codehaus

-0.55

 Porém

-0.52

/*++

-0.51

 sustains

-0.48

 wish

-0.48

||}

-0.48

POSITIVE LOGITS

 comedy

1.23

 Comedy

1.21

Comedy

1.15

comedy

1.14

 comedies

1.02

 Minang

0.92

 Medan

0.80

 Pekan

0.79

 Kome

0.79

 applau

0.78

Activations Density 0.370%

words related to comedy or comedic elements

No Comments

No Known Activations