INDEX

Explanations

words related to contrasts or comparisons

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>

-1.38

 Ohio

-0.60

 Washington

-0.59

Cuidado

-0.59

session

-0.58

Больше

-0.58

pulumi

-0.58

 death

-0.58

প্র

-0.57

Session

-0.57

POSITIVE LOGITS

vhs

1.28

 hentai

1.25

 jurassic

1.12

 sputnik

1.11

 indestru

1.11

 milf

1.10

 valentino

1.10

 wikihow

1.09

 genshin

1.08

 erad

1.08

Activations Density 0.516%

words related to contrasts or comparisons

No Comments

No Known Activations