INDEX

Explanations

words related to technology and innovation, particularly focusing on silicon-related terms

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

 faceva

-0.73

 doveva

-0.65

 conosce

-0.61

 kasa

-0.61

 Lampung

-0.59

 Bekasi

-0.58

 veniva

-0.58

 Tangerang

-0.58

 Makassar

-0.56

 interessa

-0.56

POSITIVE LOGITS

Si

1.11

Si

1.07

si

0.97

SI

0.90

si

0.89

SI

0.83

 silicon

0.81

 Sire

0.77

SIR

0.74

 Sira

0.73

Activations Density 0.162%

words related to technology and innovation, particularly focusing on silicon-related terms

No Comments

No Known Activations