INDEX

Explanations

personal pronouns related to oneself

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>

-2.88

 springfox

-0.77

 guma

-0.69

EndProject

-0.68

lateinit

-0.66

 jakarta

-0.65

 säkert

-0.62

/**

-0.61

</tbody>

-0.58

POSITIVE LOGITS

 disreg

1.23

 unlaw

1.18

 malheure

1.16

 habile

1.15

 véhic

1.15

 shenan

1.15

 héro

1.10

 effray

1.08

 accla

1.07

 expéri

1.05

Activations Density 0.117%

personal pronouns related to oneself

No Comments

No Known Activations