INDEX

Explanations

references to studies and data supporting ideological complexity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.41

ⓧ

-0.90

-0.85

/**

-0.82

USTAIN

-0.70

 springfox

-0.68

(;;)

-0.65

<?

-0.64

Transcripción

-0.59

 bonté

-0.58

POSITIVE LOGITS

 lele

1.19

 maneu

1.09

 accla

1.07

 kasa

1.03

ftu

1.03

 Karakter

1.01

kac

1.00

 inev

1.00

 kaos

0.99

mû

0.98

Activations Density 0.214%

references to studies and data supporting ideological complexity

No Comments

No Known Activations