INDEX

Explanations

strings of text characters that resemble commands or communication in a digital context

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

<bos>

-0.78

RegressionTest

-0.71

OrNil

-0.71

Autoritní

-0.69

verwijspagina

-0.65

 ivelany

-0.65

Podob

-0.61

Prí

-0.61

Jako

-0.61

Демографія

-0.60

POSITIVE LOGITS

 keramik

1.00

 lancia

0.96

 maksi

0.92

 silikon

0.91

 kafe

0.91

 melat

0.89

 seksi

0.85

 akus

0.85

 mikrofon

0.85

 alkoh

0.84

Activations Density 0.089%

strings of text characters that resemble commands or communication in a digital context

No Comments

No Known Activations